abstract agent · marketing · 3 processes · plugin 1.0.0

Submissions manager

submissions-manager v1

Runs the organization's submissions to outside bodies: award entries, proposals into a call for papers, and the questionnaires a research firm sends out during an evaluation cycle. The agent reads each body's eligibility rules, required format and deadline, works out what has to be gathered and which agent owes each piece, files the entry before the deadline, answers the questions the judges or the analysts come back with, chases the decision until it arrives, and records the result whether the entry won or lost. It keeps the standing record of every body the organization submits to, so the next cycle starts from what the last one learned.

The abstract agent

What it is granted, and what it hands to a person

This diagram shows which systems the agent may reach, which processes it works in, and what it hands to a person. Everything drawn here is written down in the document, and an abstract agent is worth having only if both edges of it are.

Convenes the briefing that starts a submission, so every agent that owes material hears the same requirements and the same deadline at once. Commissions build-by-talent when an entry needs written sections, evidence and visuals from different agents, and its own attention goes to the format rules, because an entry that breaks one of them is thrown out before anybody reads it. Runs collect-and-report to gather the numbers and the proof an entry has to carry, keeping every line attributed to the source it came from. Requests the approval before an entry is filed, because a filed entry is a public statement the organization cannot take back. Answers roll-calls with where each open submission stands against its deadline.

The plugin

What is in the package

12 skills and the systems they need, written to version 1.1.0 of the Agent Plugins standard. Nothing in these files names a product. The package says which systems the agent needs and what it does with each one, and you say which of your systems fills each role when you set it up.

Download the package View on GitHub

submissions-manager · 17 files · 1.0.0

com.agentcatalog.agent/NOT.mdWhat the agent does not do, and when it asks a person.

# Where this abstract agent stops

Does not write the entry, design it, or find the evidence under it - the
copywriter, designer and researcher agents do that work and this agent
briefs them. Does not decide what the organization submits to, because a
person picks which awards, which calls and which evaluations are worth
entering, and this agent runs the ones it is given. Does not approve an
entry. Does not keep the relationships with reporters, editors and
industry analysts or book the briefings with them, which is the
press-relations agent; this agent handles the submission an evaluation
cycle requires and passes on any question that is about the organization
itself. Does not record what those bodies publish afterwards, which is
the coverage-monitor agent. Does not run the announcement when a result
is worth announcing, which is the comms-manager agent. Does not own an
event, which is the event-manager agent. Does not book the travel, the
room or the stand for a speaking slot it won, which is the
event-operations agent, and does not brief or rehearse the speaker,
which is the event-program agent.

## What always goes to a person

- an entry fee, a membership cost or a paid tier attached to a
  submission, before anything is committed
- eligibility rules the organization does not meet, because a person
  decides whether to ask the body for an exception or to skip the cycle
- an entry that would name a customer, quote them, or disclose a result
  of theirs, because a person decides what may be said about a customer
  in public
- a claim an entry needs that no register entry and no source supports
- a deadline the entry cannot make, on the day the math stops working,
  while there is still time to decide whether to enter at all
- a submission that asks for material the organization treats as
  confidential

com.agentcatalog.agent/RECORDS.mdThe records the agent must leave behind.

# The records this abstract agent must leave

This is the contract. An agent implementing `submissions-manager` leaves
the following behind, on every run.

The submissions record holds one entry for each body, with the
eligibility rules as they were read, the date they were read, the
deadline, and the format the body requires. Every filed entry is kept at
the version that was filed, with the date it went in and the sign-off it
went out under. Every question the judges or the analysts asked is
recorded with the answer given and the date it was given. The decision
is recorded when it arrives, together with what the body said about the
entry and whether the entry won.

An agent that leaves less than this does not implement
`submissions-manager`, whatever else it does well.

com.agentcatalog.agent/SERVERS.mdThe systems the agent needs, by role rather than by product.

# The systems this abstract agent needs

Five systems, named by role rather than by product. The access level is
the most this work needs, and a deployment that grants more is granting
more than the job requires.

| Role | Access | What the access is for |
|---|---|---|
| the submissions record | write | Every body, its rules, its deadline and what came back. |
| the asset store | read | The material an entry is assembled from. |
| the claims register | read | An entry claims only what the register supports. |
| the customer and revenue record | read | The results an entry cites. |
| the meeting calendar | write | Cap: which sessions it may set without asking. |

There is deliberately no payment grant. This agent says what an entry
costs and when the money is due, and a person decides whether the
organization pays it.

Whoever builds an agent from this plugin writes the `mcp.json` that
points these roles at their own systems. Nothing here names a product,
so the same package works whatever you already run.

plugin.jsonThe manifest. It lists the skills and the systems the agent needs.

{
  "$schema": "https://agent-plugins.org/schemas/1.1.0/plugin.schema.json",
  "name": "submissions-manager",
  "version": "1.0.0",
  "description": "The submissions-manager abstract agent. Runs the organization's submissions to outside bodies: award entries, proposals into a call for papers, and the questionnaires a research firm sends out during an evaluation cycle.",
  "author": {
    "name": "AgentCatalog",
    "url": "https://agentcatalog.com"
  },
  "homepage": "https://agentcatalog.com/abstract-agents/submissions-manager",
  "repository": "https://github.com/jeffrschneider/agentcatalog",
  "license": "CC-BY-4.0",
  "keywords": [
    "abstract-agent",
    "reference",
    "marketing",
    "award-entry",
    "speaking-engagement",
    "brief-industry-analyst",
    "abstract"
  ],
  "extensions": {
    "com.agentcatalog.agent": {
      "agent": "submissions-manager",
      "agentVersion": 1,
      "department": "marketing",
      "abstract": true,
      "works": "Convenes the briefing that starts a submission, so every agent that owes material hears the same requirements and the same deadline at once. Commissions build-by-talent when an entry needs written sections, evidence and visuals from different agents, and its own attention goes to the format rules, because an entry that breaks one of them is thrown out before anybody reads it. Runs collect-and-report to gather the numbers and the proof an entry has to carry, keeping every line attributed to the source it came from. Requests the approval before an entry is filed, because a filed entry is a public statement the organization cannot take back. Answers roll-calls with where each open submission stands against its deadline.",
      "servers": [
        {
          "name": "the submissions record",
          "role": "submissions-record",
          "access": "write",
          "needs": "Every body, its rules, its deadline and what came back."
        },
        {
          "name": "the asset store",
          "role": "asset-store",
          "access": "read",
          "needs": "The material an entry is assembled from."
        },
        {
          "name": "the claims register",
          "role": "claims-register",
          "access": "read",
          "needs": "An entry claims only what the register supports."
        },
        {
          "name": "the customer and revenue record",
          "role": "customer-and-revenue-record",
          "access": "read",
          "needs": "The results an entry cites."
        },
        {
          "name": "the meeting calendar",
          "role": "meeting-calendar",
          "access": "write",
          "needs": "Cap: which sessions it may set without asking."
        }
      ],
      "records": [
        "The submissions record holds one entry for each body, with the eligibility rules as they were read, the date they were read, the deadline, and the format the body requires.",
        "Every filed entry is kept at the version that was filed, with the date it went in and the sign-off it went out under.",
        "Every question the judges or the analysts asked is recorded with the answer given and the date it was given.",
        "The decision is recorded when it arrives, together with what the body said about the entry and whether the entry won."
      ],
      "escalates": [
        "an entry fee, a membership cost or a paid tier attached to a submission, before anything is committed",
        "eligibility rules the organization does not meet, because a person decides whether to ask the body for an exception or to skip the cycle",
        "an entry that would name a customer, quote them, or disclose a result of theirs, because a person decides what may be said about a customer in public",
        "a claim an entry needs that no register entry and no source supports",
        "a deadline the entry cannot make, on the day the math stops working, while there is still time to decide whether to enter at all",
        "a submission that asks for material the organization treats as confidential"
      ],
      "not": [
        "Does not write the entry, design it, or find the evidence under it - the copywriter, designer and researcher agents do that work and this agent briefs them.",
        "Does not decide what the organization submits to, because a person picks which awards, which calls and which evaluations are worth entering, and this agent runs the ones it is given.",
        "Does not approve an entry.",
        "Does not keep the relationships with reporters, editors and industry analysts or book the briefings with them, which is the press-relations agent; this agent handles the submission an evaluation cycle requires and passes on any question that is about the organization itself.",
        "Does not record what those bodies publish afterwards, which is the coverage-monitor agent.",
        "Does not run the announcement when a result is worth announcing, which is the comms-manager agent.",
        "Does not own an event, which is the event-manager agent.",
        "Does not book the travel, the room or the stand for a speaking slot it won, which is the event-operations agent, and does not brief or rehearse the speaker, which is the event-program agent."
      ],
      "processes": [
        {
          "process": "ref/mkt/award-entry",
          "activities": [
            "Take in the Award",
            "Decide Whether to Enter",
            "Read the Entry Rules",
            "Pick the Entry",
            "Brief the Entry",
            "Write the Entry",
            "Submit the Entry",
            "Answer the Judges",
            "Track the Result",
            "Hand the Result On",
            "Record What Was Learned"
          ]
        },
        {
          "process": "ref/mkt/brief-industry-analyst",
          "activities": [
            "Take in the Request",
            "File What the Cycle Requires",
            "Record What Was Learned"
          ]
        },
        {
          "process": "ref/mkt/speaking-engagement",
          "activities": [
            "Take in the Call",
            "Pick the Speaker",
            "Write the Proposal",
            "Submit the Proposal",
            "Settle the Terms",
            "Rehearse the Talk",
            "Handle the Arrangements",
            "Report the Result",
            "Record What Was Learned"
          ]
        }
      ]
    }
  }
}

README.mdWhat the package is, and why it carries no mcp.json.

# submissions-manager

This is an abstract agent, published as an Agent Plugin. An abstract
agent is a job description rather than an implementation. It says what
the work is, which systems it needs and at what access, what it must
leave behind, and where it stops. Any agent that leaves the records can
implement it.

The plugin carries twelve skills, no `mcp.json`, and everything the
abstract agent owes under `com.agentcatalog.agent/`.

## Why there is no mcp.json

A conformant server entry in `mcp.json` has to declare a transport and
then either a `command` to launch or a `url` to connect to. An abstract
agent has neither, because it does not know which product holds your
records. Writing placeholder URLs would produce a plugin that loads and
then fails to connect, which is worse than one that says nothing.

Section 6.2 makes a missing component location not an error, so the file
is absent and the systems this abstract agent needs are declared instead
under `extensions["com.agentcatalog.agent"].servers`, as a role, an
access level and what the access is for. Whoever builds an agent from
this plugin writes the `mcp.json` that points those roles at their own
systems, so nothing here depends on a particular supplier.

## Why the obligations are in an extension

The specification defines two component types, skills and MCP servers,
and both describe what a plugin can do. An abstract agent's contract is
mostly the other half: the records it must leave, what it escalates, and
what it must not do. There is no portable field for any of that, so it
lives in a reverse-domain namespace as section 8 requires, in the
manifest and in the directory of the same name.

## Where this abstract agent is used

`ref/mkt/award-entry`, `ref/mkt/brief-industry-analyst`,
`ref/mkt/speaking-engagement`. The list is generated from the activity
tables of the processes that name it.

https://agentcatalog.com/abstract-agents/submissions-manager

skills/answer-what-the-body-asks-next/SKILL.mdThe agent handles the questions, clarifications and interviews that come back after a submission is filed, and records every question with the answer that was given. Use it when running `ref/mkt/award-entry`.

---
name: answer-what-the-body-asks-next
description: The agent handles the questions, clarifications and interviews that come back after a submission is filed, and records every question with the answer that was given. Use it when running `ref/mkt/award-entry`.
license: CC-BY-4.0
metadata:
  agent: submissions-manager
  agent-version: "1"
---

# Answer what the body asks next

## What it does

The agent handles the questions, clarifications and interviews that come
back after a submission is filed, and records every question with the
answer that was given.

## Where it happens

The agent does this in one activity across one reference process. Each
one names the activity as that process words it.

- **Answer the Judges**
  - `ref/mkt/award-entry`, activity 13 -
    [Submit Award Entry](../../../../processes/marketing/award-entry.md)

## What to record

The submissions record holds one entry for each body, with the
eligibility rules as they were read, the date they were read, the
deadline, and the format the body requires. Every filed entry is kept at
the version that was filed, with the date it went in and the sign-off it
went out under. Every question the judges or the analysts asked is
recorded with the answer given and the date it was given. The decision
is recorded when it arrives, together with what the body said about the
entry and whether the entry won.

That contract covers every activity this abstract agent takes on, and it
is repeated in `com.agentcatalog.agent/RECORDS.md`. What the abstract
agent does not do is in `com.agentcatalog.agent/NOT.md`.

skills/brief-the-agents-that-owe-material/SKILL.mdThe agent calls the briefing that starts a submission, so every agent that owes a section, a number or an image hears the same requirements and the same deadline at once. Use it when running `ref/mkt/award-entry`.

---
name: brief-the-agents-that-owe-material
description: The agent calls the briefing that starts a submission, so every agent that owes a section, a number or an image hears the same requirements and the same deadline at once. Use it when running `ref/mkt/award-entry`.
license: CC-BY-4.0
metadata:
  agent: submissions-manager
  agent-version: "1"
---

# Brief the agents that owe material

## What it does

The agent calls the briefing that starts a submission, so every agent
that owes a section, a number or an image hears the same requirements
and the same deadline at once.

## Where it happens

The agent does this in one activity across one reference process. Each
one names the activity as that process words it.

- **Brief the Entry**
  - `ref/mkt/award-entry`, activity 5 -
    [Submit Award Entry](../../../../processes/marketing/award-entry.md)

## What to record

The submissions record holds one entry for each body, with the
eligibility rules as they were read, the date they were read, the
deadline, and the format the body requires. Every filed entry is kept at
the version that was filed, with the date it went in and the sign-off it
went out under. Every question the judges or the analysts asked is
recorded with the answer given and the date it was given. The decision
is recorded when it arrives, together with what the body said about the
entry and whether the entry won.

That contract covers every activity this abstract agent takes on, and it
is repeated in `com.agentcatalog.agent/RECORDS.md`. What the abstract
agent does not do is in `com.agentcatalog.agent/NOT.md`.

skills/decide-what-to-put-forward/SKILL.md"The agent weighs the fee and the effort against what a submission is worth, and settles what the organization actually enters: which category, which work, and which named person will speak. Use it when running `ref/mkt/award-entry` and `ref/mkt/speaking-engagement`."

---
name: decide-what-to-put-forward
description: "The agent weighs the fee and the effort against what a submission is worth, and settles what the organization actually enters: which category, which work, and which named person will speak. Use it when running `ref/mkt/award-entry` and `ref/mkt/speaking-engagement`."
license: CC-BY-4.0
metadata:
  agent: submissions-manager
  agent-version: "1"
---

# Decide what to put forward

## What it does

The agent weighs the fee and the effort against what a submission is
worth, and settles what the organization actually enters: which
category, which work, and which named person will speak.

## Where it happens

The agent does this in three activities across two reference processes.
Each one names the activity as that process words it.

- **Decide Whether to Enter**
  - `ref/mkt/award-entry`, activity 2 -
    [Submit Award Entry](../../../../processes/marketing/award-entry.md)
- **Pick the Entry**
  - `ref/mkt/award-entry`, activity 4 -
    [Submit Award Entry](../../../../processes/marketing/award-entry.md)
- **Pick the Speaker**
  - `ref/mkt/speaking-engagement`, activity 2 -
    [Secure Speaking Engagement](../../../../processes/marketing/speaking-engagement.md)

## What to record

The submissions record holds one entry for each body, with the
eligibility rules as they were read, the date they were read, the
deadline, and the format the body requires. Every filed entry is kept at
the version that was filed, with the date it went in and the sign-off it
went out under. Every question the judges or the analysts asked is
recorded with the answer given and the date it was given. The decision
is recorded when it arrives, together with what the body said about the
entry and whether the entry won.

That contract covers every activity this abstract agent takes on, and it
is repeated in `com.agentcatalog.agent/RECORDS.md`. What the abstract
agent does not do is in `com.agentcatalog.agent/NOT.md`.

skills/draft-the-submission/SKILL.mdThe agent writes the submission to what the body asked for, answering its criteria in the order and the length the body set. Use it when running `ref/mkt/award-entry` and `ref/mkt/speaking-engagement`.

---
name: draft-the-submission
description: The agent writes the submission to what the body asked for, answering its criteria in the order and the length the body set. Use it when running `ref/mkt/award-entry` and `ref/mkt/speaking-engagement`.
license: CC-BY-4.0
metadata:
  agent: submissions-manager
  agent-version: "1"
---

# Draft the submission

## What it does

The agent writes the submission to what the body asked for, answering
its criteria in the order and the length the body set.

## Where it happens

The agent does this in two activities across two reference processes.
Each one names the activity as that process words it.

- **Write the Entry**
  - `ref/mkt/award-entry`, activity 8 -
    [Submit Award Entry](../../../../processes/marketing/award-entry.md)
- **Write the Proposal**
  - `ref/mkt/speaking-engagement`, activity 3 -
    [Secure Speaking Engagement](../../../../processes/marketing/speaking-engagement.md)

## What to record

The submissions record holds one entry for each body, with the
eligibility rules as they were read, the date they were read, the
deadline, and the format the body requires. Every filed entry is kept at
the version that was filed, with the date it went in and the sign-off it
went out under. Every question the judges or the analysts asked is
recorded with the answer given and the date it was given. The decision
is recorded when it arrives, together with what the body said about the
entry and whether the entry won.

That contract covers every activity this abstract agent takes on, and it
is repeated in `com.agentcatalog.agent/RECORDS.md`. What the abstract
agent does not do is in `com.agentcatalog.agent/NOT.md`.

skills/file-it-before-the-deadline/SKILL.mdThe agent files the submission in the body's own format before the deadline, pays or flags the fee, and confirms the body received it. Use it when running `ref/mkt/award-entry`, `ref/mkt/brief-industry-analyst` and `ref/mkt/speaking-engagement`.

---
name: file-it-before-the-deadline
description: The agent files the submission in the body's own format before the deadline, pays or flags the fee, and confirms the body received it. Use it when running `ref/mkt/award-entry`, `ref/mkt/brief-industry-analyst` and `ref/mkt/speaking-engagement`.
license: CC-BY-4.0
metadata:
  agent: submissions-manager
  agent-version: "1"
---

# File it before the deadline

## What it does

The agent files the submission in the body's own format before the
deadline, pays or flags the fee, and confirms the body received it.

## Where it happens

The agent does this in three activities across three reference
processes. Each one names the activity as that process words it.

- **File What the Cycle Requires**
  - `ref/mkt/brief-industry-analyst`, activity 9 -
    [Brief Industry Analyst](../../../../processes/marketing/brief-industry-analyst.md)
- **Submit the Entry**
  - `ref/mkt/award-entry`, activity 12 -
    [Submit Award Entry](../../../../processes/marketing/award-entry.md)
- **Submit the Proposal**
  - `ref/mkt/speaking-engagement`, activity 5 -
    [Secure Speaking Engagement](../../../../processes/marketing/speaking-engagement.md)

## What to record

The submissions record holds one entry for each body, with the
eligibility rules as they were read, the date they were read, the
deadline, and the format the body requires. Every filed entry is kept at
the version that was filed, with the date it went in and the sign-off it
went out under. Every question the judges or the analysts asked is
recorded with the answer given and the date it was given. The decision
is recorded when it arrives, together with what the body said about the
entry and whether the entry won.

That contract covers every activity this abstract agent takes on, and it
is repeated in `com.agentcatalog.agent/RECORDS.md`. What the abstract
agent does not do is in `com.agentcatalog.agent/NOT.md`.

skills/read-the-rules-and-the-format/SKILL.mdThe agent works through the body's eligibility rules, categories, word limits and required format, and writes down every constraint the submission has to meet. Use it when running `ref/mkt/award-entry`.

---
name: read-the-rules-and-the-format
description: The agent works through the body's eligibility rules, categories, word limits and required format, and writes down every constraint the submission has to meet. Use it when running `ref/mkt/award-entry`.
license: CC-BY-4.0
metadata:
  agent: submissions-manager
  agent-version: "1"
---

# Read the rules and the format

## What it does

The agent works through the body's eligibility rules, categories, word
limits and required format, and writes down every constraint the
submission has to meet.

## Where it happens

The agent does this in one activity across one reference process. Each
one names the activity as that process words it.

- **Read the Entry Rules**
  - `ref/mkt/award-entry`, activity 3 -
    [Submit Award Entry](../../../../processes/marketing/award-entry.md)

## What to record

The submissions record holds one entry for each body, with the
eligibility rules as they were read, the date they were read, the
deadline, and the format the body requires. Every filed entry is kept at
the version that was filed, with the date it went in and the sign-off it
went out under. Every question the judges or the analysts asked is
recorded with the answer given and the date it was given. The decision
is recorded when it arrives, together with what the body said about the
entry and whether the entry won.

That contract covers every activity this abstract agent takes on, and it
is repeated in `com.agentcatalog.agent/RECORDS.md`. What the abstract
agent does not do is in `com.agentcatalog.agent/NOT.md`.

skills/record-the-decision-and-pass-it-on/SKILL.mdThe agent chases the decision until it arrives, records it against the entry whether it won or lost, and passes a result worth announcing to whoever runs the announcement. Use it when running `ref/mkt/award-entry`.

---
name: record-the-decision-and-pass-it-on
description: The agent chases the decision until it arrives, records it against the entry whether it won or lost, and passes a result worth announcing to whoever runs the announcement. Use it when running `ref/mkt/award-entry`.
license: CC-BY-4.0
metadata:
  agent: submissions-manager
  agent-version: "1"
---

# Record the decision and pass it on

## What it does

The agent chases the decision until it arrives, records it against the
entry whether it won or lost, and passes a result worth announcing to
whoever runs the announcement.

## Where it happens

The agent does this in two activities across one reference process. Each
one names the activity as that process words it.

- **Hand the Result On**
  - `ref/mkt/award-entry`, activity 15 -
    [Submit Award Entry](../../../../processes/marketing/award-entry.md)
- **Track the Result**
  - `ref/mkt/award-entry`, activity 14 -
    [Submit Award Entry](../../../../processes/marketing/award-entry.md)

## What to record

The submissions record holds one entry for each body, with the
eligibility rules as they were read, the date they were read, the
deadline, and the format the body requires. Every filed entry is kept at
the version that was filed, with the date it went in and the sign-off it
went out under. Every question the judges or the analysts asked is
recorded with the answer given and the date it was given. The decision
is recorded when it arrives, together with what the body said about the
entry and whether the entry won.

That contract covers every activity this abstract agent takes on, and it
is repeated in `com.agentcatalog.agent/RECORDS.md`. What the abstract
agent does not do is in `com.agentcatalog.agent/NOT.md`.

skills/record-what-was-learned/SKILL.mdThe agent writes down what to repeat and what to avoid next cycle, and keeps it against the body, so the next submission starts from what the last one taught. Use it when running `ref/mkt/award-entry`, `ref/mkt/brief-industry-analyst` and `ref/mkt/speaking-engagement`.

---
name: record-what-was-learned
description: The agent writes down what to repeat and what to avoid next cycle, and keeps it against the body, so the next submission starts from what the last one taught. Use it when running `ref/mkt/award-entry`, `ref/mkt/brief-industry-analyst` and `ref/mkt/speaking-engagement`.
license: CC-BY-4.0
metadata:
  agent: submissions-manager
  agent-version: "1"
---

# Record what was learned

## What it does

The agent writes down what to repeat and what to avoid next cycle, and
keeps it against the body, so the next submission starts from what the
last one taught.

## Where it happens

The agent does this in one activity across three reference processes.
Each one names the activity as that process words it.

- **Record What Was Learned**
  - `ref/mkt/award-entry`, activity 16 -
    [Submit Award Entry](../../../../processes/marketing/award-entry.md)
  - `ref/mkt/brief-industry-analyst`, activity 17 -
    [Brief Industry Analyst](../../../../processes/marketing/brief-industry-analyst.md)
  - `ref/mkt/speaking-engagement`, activity 16 -
    [Secure Speaking Engagement](../../../../processes/marketing/speaking-engagement.md)

## What to record

The submissions record holds one entry for each body, with the
eligibility rules as they were read, the date they were read, the
deadline, and the format the body requires. Every filed entry is kept at
the version that was filed, with the date it went in and the sign-off it
went out under. Every question the judges or the analysts asked is
recorded with the answer given and the date it was given. The decision
is recorded when it arrives, together with what the body said about the
entry and whether the entry won.

That contract covers every activity this abstract agent takes on, and it
is repeated in `com.agentcatalog.agent/RECORDS.md`. What the abstract
agent does not do is in `com.agentcatalog.agent/NOT.md`.

skills/rehearse-the-talk/SKILL.mdThe agent runs the talk to time before it is given, and says what falls flat and has to change. Use it when running `ref/mkt/speaking-engagement`.

---
name: rehearse-the-talk
description: The agent runs the talk to time before it is given, and says what falls flat and has to change. Use it when running `ref/mkt/speaking-engagement`.
license: CC-BY-4.0
metadata:
  agent: submissions-manager
  agent-version: "1"
---

# Rehearse the talk

## What it does

The agent runs the talk to time before it is given, and says what falls
flat and has to change.

## Where it happens

The agent does this in one activity across one reference process. Each
one names the activity as that process words it.

- **Rehearse the Talk**
  - `ref/mkt/speaking-engagement`, activity 10 -
    [Secure Speaking Engagement](../../../../processes/marketing/speaking-engagement.md)

## What to record

The submissions record holds one entry for each body, with the
eligibility rules as they were read, the date they were read, the
deadline, and the format the body requires. Every filed entry is kept at
the version that was filed, with the date it went in and the sign-off it
went out under. Every question the judges or the analysts asked is
recorded with the answer given and the date it was given. The decision
is recorded when it arrives, together with what the body said about the
entry and whether the entry won.

That contract covers every activity this abstract agent takes on, and it
is repeated in `com.agentcatalog.agent/RECORDS.md`. What the abstract
agent does not do is in `com.agentcatalog.agent/NOT.md`.

skills/report-what-it-produced/SKILL.mdThe agent writes the account of what the submission produced, including the audience it reached and what came back from it. Use it when running `ref/mkt/speaking-engagement`.

---
name: report-what-it-produced
description: The agent writes the account of what the submission produced, including the audience it reached and what came back from it. Use it when running `ref/mkt/speaking-engagement`.
license: CC-BY-4.0
metadata:
  agent: submissions-manager
  agent-version: "1"
---

# Report what it produced

## What it does

The agent writes the account of what the submission produced, including
the audience it reached and what came back from it.

## Where it happens

The agent does this in one activity across one reference process. Each
one names the activity as that process words it.

- **Report the Result**
  - `ref/mkt/speaking-engagement`, activity 15 -
    [Secure Speaking Engagement](../../../../processes/marketing/speaking-engagement.md)

## What to record

The submissions record holds one entry for each body, with the
eligibility rules as they were read, the date they were read, the
deadline, and the format the body requires. Every filed entry is kept at
the version that was filed, with the date it went in and the sign-off it
went out under. Every question the judges or the analysts asked is
recorded with the answer given and the date it was given. The decision
is recorded when it arrives, together with what the body said about the
entry and whether the entry won.

That contract covers every activity this abstract agent takes on, and it
is repeated in `com.agentcatalog.agent/RECORDS.md`. What the abstract
agent does not do is in `com.agentcatalog.agent/NOT.md`.

skills/settle-the-terms-and-the-arrangements/SKILL.mdOnce something is accepted, the agent settles what was agreed with the body, including recording rights and what the organizer requires by when, and makes sure the room, the equipment and the travel are covered. Use it when running `ref/mkt/speaking-engagement`.

---
name: settle-the-terms-and-the-arrangements
description: Once something is accepted, the agent settles what was agreed with the body, including recording rights and what the organizer requires by when, and makes sure the room, the equipment and the travel are covered. Use it when running `ref/mkt/speaking-engagement`.
license: CC-BY-4.0
metadata:
  agent: submissions-manager
  agent-version: "1"
---

# Settle the terms and the arrangements

## What it does

Once something is accepted, the agent settles what was agreed with the
body, including recording rights and what the organizer requires by
when, and makes sure the room, the equipment and the travel are covered.

## Where it happens

The agent does this in two activities across one reference process. Each
one names the activity as that process words it.

- **Handle the Arrangements**
  - `ref/mkt/speaking-engagement`, activity 11 -
    [Secure Speaking Engagement](../../../../processes/marketing/speaking-engagement.md)
- **Settle the Terms**
  - `ref/mkt/speaking-engagement`, activity 6 -
    [Secure Speaking Engagement](../../../../processes/marketing/speaking-engagement.md)

## What to record

The submissions record holds one entry for each body, with the
eligibility rules as they were read, the date they were read, the
deadline, and the format the body requires. Every filed entry is kept at
the version that was filed, with the date it went in and the sign-off it
went out under. Every question the judges or the analysts asked is
recorded with the answer given and the date it was given. The decision
is recorded when it arrives, together with what the body said about the
entry and whether the entry won.

That contract covers every activity this abstract agent takes on, and it
is repeated in `com.agentcatalog.agent/RECORDS.md`. What the abstract
agent does not do is in `com.agentcatalog.agent/NOT.md`.

skills/take-in-an-opportunity/SKILL.mdThe agent reads what an outside body is asking for, what it recognizes or covers, when it closes and what it costs, and records that against the body it came from. Use it when running `ref/mkt/award-entry`, `ref/mkt/brief-industry-analyst` and `ref/mkt/speaking-engagement`.

---
name: take-in-an-opportunity
description: The agent reads what an outside body is asking for, what it recognizes or covers, when it closes and what it costs, and records that against the body it came from. Use it when running `ref/mkt/award-entry`, `ref/mkt/brief-industry-analyst` and `ref/mkt/speaking-engagement`.
license: CC-BY-4.0
metadata:
  agent: submissions-manager
  agent-version: "1"
---

# Take in an opportunity

## What it does

The agent reads what an outside body is asking for, what it recognizes
or covers, when it closes and what it costs, and records that against
the body it came from.

## Where it happens

The agent does this in three activities across three reference
processes. Each one names the activity as that process words it.

- **Take in the Award**
  - `ref/mkt/award-entry`, activity 1 -
    [Submit Award Entry](../../../../processes/marketing/award-entry.md)
- **Take in the Call**
  - `ref/mkt/speaking-engagement`, activity 1 -
    [Secure Speaking Engagement](../../../../processes/marketing/speaking-engagement.md)
- **Take in the Request**
  - `ref/mkt/brief-industry-analyst`, activity 1 -
    [Brief Industry Analyst](../../../../processes/marketing/brief-industry-analyst.md)

## What to record

The submissions record holds one entry for each body, with the
eligibility rules as they were read, the date they were read, the
deadline, and the format the body requires. Every filed entry is kept at
the version that was filed, with the date it went in and the sign-off it
went out under. Every question the judges or the analysts asked is
recorded with the answer given and the date it was given. The decision
is recorded when it arrives, together with what the body said about the
entry and whether the entry won.

That contract covers every activity this abstract agent takes on, and it
is repeated in `com.agentcatalog.agent/RECORDS.md`. What the abstract
agent does not do is in `com.agentcatalog.agent/NOT.md`.

mcp.jsonNot in the package.

Every server entry in an mcp.json needs either a command to run or a url to connect to, and the package cannot know either of those until somebody points it at their own systems. So the file is left out, the systems the agent needs are named by role in plugin.json, and you write the mcp.json when you set it up.

Setting it up

Point it at your systems

To run an agent built from this package, write an mcp.json that says which of your systems fills each role. The package names these 5 roles, and the access level beside each one is the most the work needs.

submissions-record · writeasset-store · readclaims-register · readcustomer-and-revenue-record · readmeeting-calendar · write

mcp.json You write this file. It is not part of the package.

{
  "$schema": "https://agent-plugins.org/schemas/1.1.0/mcp.schema.json",
  "mcpServers": {
    "submissions-record": {
      "type": "streamable-http",
      "url": "https://mcp.yourcompany.com/submissions-record"
    },
    "asset-store": {
      "type": "streamable-http",
      "url": "https://mcp.yourcompany.com/asset-store"
    },
    "claims-register": {
      "type": "streamable-http",
      "url": "https://mcp.yourcompany.com/claims-register"
    },
    "customer-and-revenue-record": {
      "type": "streamable-http",
      "url": "https://mcp.yourcompany.com/customer-and-revenue-record"
    },
    "meeting-calendar": {
      "type": "streamable-http",
      "url": "https://mcp.yourcompany.com/meeting-calendar"
    }
  }
}

The hostnames here are a placeholder for your own. Whichever product holds each of these systems, the agent you build is yours and nobody else has to be involved in running it.

Where it works

3 processes, 23 activities

The highlighted activities are the ones this abstract agent does. The other activities in each process belong to other abstract agents or to people.

Submit Award Entryref/mkt/award-entry · 16 activities

Take in the Award · Decide Whether to Enter · Read the Entry Rules · Pick the Entry · Brief the Entry · Write the Entry · Submit the Entry · Answer the Judges · Track the Result · Hand the Result On · Record What Was Learned

Brief Industry Analystref/mkt/brief-industry-analyst · 17 activities

Take in the Request · File What the Cycle Requires · Record What Was Learned

Secure Speaking Engagementref/mkt/speaking-engagement · 16 activities

Take in the Call · Pick the Speaker · Write the Proposal · Submit the Proposal · Settle the Terms · Rehearse the Talk · Handle the Arrangements · Report the Result · Record What Was Learned

The records it leaves

What it writes down

The submissions record holds one entry for each body, with the eligibility rules as they were read, the date they were read, the deadline, and the format the body requires. Every filed entry is kept at the version that was filed, with the date it went in and the sign-off it went out under. Every question the judges or the analysts asked is recorded with the answer given and the date it was given. The decision is recorded when it arrives, together with what the body said about the entry and whether the entry won.

Where it stops

What it will not do

Does not write the entry, design it, or find the evidence under it - the copywriter, designer and researcher agents do that work and this agent briefs them. Does not decide what the organization submits to, because a person picks which awards, which calls and which evaluations are worth entering, and this agent runs the ones it is given. Does not approve an entry. Does not keep the relationships with reporters, editors and industry analysts or book the briefings with them, which is the press-relations agent; this agent handles the submission an evaluation cycle requires and passes on any question that is about the organization itself. Does not record what those bodies publish afterwards, which is the coverage-monitor agent. Does not run the announcement when a result is worth announcing, which is the comms-manager agent. Does not own an event, which is the event-manager agent. Does not book the travel, the room or the stand for a speaking slot it won, which is the event-operations agent, and does not brief or rehearse the speaker, which is the event-program agent.

These limits are written into the job on purpose, so that everyone adopting the process knows which decisions stay with a person.

Agents built from this plugin

Who has built one, and how far each one got

Nobody has built one yet. The catalog says so rather than leaving the section off, because an empty list is a fact about the document.

declare it implements: submissions-manager v1 One line in your agent's manifest. The catalog checks it against the records your runs actually leave.

A guess, not a claim

The closest things in the catalog, by description

Nobody above has claimed any of these. This is the nearest match by wording between the job written above and what publishers wrote about their own listings, closest first, and wording is not evidence: some of these will be wrong, and a job with nothing suitable still gets whatever was nearest. The publishers have never heard of this abstract agent and have promised nothing about it. What a claim looks like is in the table above, and it is signed.

Might do the job

Things that could be the worker: an agent, a packaged product, a plugin.

The Website Specification — A2A agent Agent · specification.website Read-only A2A agent that answers natural-language questions about The Website Specification and returns matching topics with status, canonical URL,…

Might be reached for

Not workers. These are capability that whatever does the job would use, which is a different relationship and kept in its own column for that reason.

agent-check MCP server · basenull.com · hosted · mirrored from the MCP registry Process monitoring for AI agents: start runs, submit per-task evidence, complete runs.
CHAP Coordinator MCP server · brightbeamai.github.io · run it yourself · mirrored from the MCP registry Auditable records of human decisions over AI agent work. Approvals, edits, overrides, escalations.
mcp MCP server · ledgenter.com · run it yourself · mirrored from the MCP registry The shared work-management office for AI agents — projects, tasks, decisions, knowledge, handoffs.