abstract agent · partners · 2 processes · plugin 1.0.0

Alliance scout

alliance-scout v1

Works out why the company would work with another company at all, and tests whether a named candidate actually fits before anybody drafts anything. It writes the strategic reason down first, checks whether building or buying would answer it better, scans the field, reads what each candidate sells and to whom, and scores each one against the reason the run started. It carries the shortlist to first contact, sees mutual confidentiality signed before either side shows anything real, and ends with a joint thesis one page long that both companies would recognize. A run that cannot state its reason does not start, and a run that stops still leaves its record for the next one.

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.

Runs collect-and-report to scan the field and to keep the candidate log open across the run. Runs assessment to score each candidate against the stated reason. Convenes the debrief that records the exploration whether it proceeded or stopped. Works with the researcher agent, which reads the candidates, and the partner-manager agent, which knows what a partner relationship already costs to run. Hands the joint thesis to the diligence-coordinator agent, and carries what our side must get into the deal-structurer agent's shaping.

The plugin

What is in the package

5 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

alliance-scout · 10 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 run the diligence on a candidate, which is the
diligence-coordinator agent, and does not model what the arrangement
would be worth or shape its terms, which is the deal-structurer agent.
Does not check for contract, customer and rival conflicts itself, which
is the supplier-check agent with the legal reviewer (person). Does not
negotiate and does not sign. Does not recruit a reseller into a channel
programme, which is the partner-manager agent's ground; this agent looks
for a strategic fit, not a route to market that already exists.

## What always goes to a person

- the decision to proceed or stop, always - to the executive sponsor and
  the alliances lead, never taken by this agent
- anything beyond public material that somebody wants shown before
  mutual confidentiality is signed
- a candidate a customer contract forbids - with the clause recorded
  against the drop
- the first approach itself - a named person makes it
- a thesis that only holds on the upside case, because a value model
  with no downside case does not go to a decision

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 `alliance-scout` leaves the
following behind, on every run.

The strategic reason as written before any company was named, dated. The
build, buy or ally comparison and what it concluded. The candidate list
with the source of each name. Per candidate: what they sell and to whom,
the fit score, the criteria it was scored on, and the inputs behind it.
The shortlist with the order of approach and who was to make it. Per
candidate approached: the date, the person who made contact, and the
mutual confidentiality agreement signed before anything beyond public
material was shown. The numbers each side traded and the agreement they
were traded under. The joint thesis at a version. The exploration
record, kept either way, readable by the next run that names the same
candidate.

An agent that leaves less than this does not implement `alliance-scout`,
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

Six 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 strategy record | write | The reason the run started and the thesis it ended with live here, at versions. |
| company data sources | read | What each candidate sells, to whom, and at what size. |
| the CRM | read | Where a candidate already touches our customers. |
| the contract system | read | A customer contract can forbid working with a candidate, and that has to be found before contact. |
| the confidentiality register | write | What was signed with whom, and on what date. |
| the partner record | write |  |

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": "alliance-scout",
  "version": "1.0.0",
  "description": "The alliance-scout abstract agent. Works out why the company would work with another company at all, and tests whether a named candidate actually fits before anybody drafts anything.",
  "author": {
    "name": "AgentCatalog",
    "url": "https://agentcatalog.com"
  },
  "homepage": "https://agentcatalog.com/abstract-agents/alliance-scout",
  "repository": "https://github.com/jeffrschneider/agentcatalog",
  "license": "CC-BY-4.0",
  "keywords": [
    "abstract-agent",
    "reference",
    "partners",
    "explore-an-alliance",
    "structure-an-alliance",
    "abstract"
  ],
  "extensions": {
    "com.agentcatalog.agent": {
      "agent": "alliance-scout",
      "agentVersion": 1,
      "department": "partners",
      "abstract": true,
      "works": "Runs collect-and-report to scan the field and to keep the candidate log open across the run. Runs assessment to score each candidate against the stated reason. Convenes the debrief that records the exploration whether it proceeded or stopped. Works with the researcher agent, which reads the candidates, and the partner-manager agent, which knows what a partner relationship already costs to run. Hands the joint thesis to the diligence-coordinator agent, and carries what our side must get into the deal-structurer agent's shaping.",
      "servers": [
        {
          "name": "the strategy record",
          "role": "strategy-record",
          "access": "write",
          "needs": "The reason the run started and the thesis it ended with live here, at versions."
        },
        {
          "name": "company data sources",
          "role": "company-data-sources",
          "access": "read",
          "needs": "What each candidate sells, to whom, and at what size."
        },
        {
          "name": "the CRM",
          "role": "crm",
          "access": "read",
          "needs": "Where a candidate already touches our customers."
        },
        {
          "name": "the contract system",
          "role": "contract-system",
          "access": "read",
          "needs": "A customer contract can forbid working with a candidate, and that has to be found before contact."
        },
        {
          "name": "the confidentiality register",
          "role": "confidentiality-register",
          "access": "write",
          "needs": "What was signed with whom, and on what date."
        },
        {
          "name": "the partner record",
          "role": "partner-record",
          "access": "write"
        }
      ],
      "records": [
        "The strategic reason as written before any company was named, dated.",
        "The build, buy or ally comparison and what it concluded.",
        "The candidate list with the source of each name.",
        "Per candidate: what they sell and to whom, the fit score, the criteria it was scored on, and the inputs behind it.",
        "The shortlist with the order of approach and who was to make it.",
        "Per candidate approached: the date, the person who made contact, and the mutual confidentiality agreement signed before anything beyond public material was shown.",
        "The numbers each side traded and the agreement they were traded under.",
        "The joint thesis at a version.",
        "The exploration record, kept either way, readable by the next run that names the same candidate."
      ],
      "escalates": [
        "the decision to proceed or stop, always - to the executive sponsor and the alliances lead, never taken by this agent",
        "anything beyond public material that somebody wants shown before mutual confidentiality is signed",
        "a candidate a customer contract forbids - with the clause recorded against the drop",
        "the first approach itself - a named person makes it",
        "a thesis that only holds on the upside case, because a value model with no downside case does not go to a decision"
      ],
      "not": [
        "Does not run the diligence on a candidate, which is the diligence-coordinator agent, and does not model what the arrangement would be worth or shape its terms, which is the deal-structurer agent.",
        "Does not check for contract, customer and rival conflicts itself, which is the supplier-check agent with the legal reviewer (person).",
        "Does not negotiate and does not sign.",
        "Does not recruit a reseller into a channel programme, which is the partner-manager agent's ground; this agent looks for a strategic fit, not a route to market that already exists."
      ],
      "processes": [
        {
          "process": "ref/prt/explore-an-alliance",
          "activities": [
            "State the Strategic Reason",
            "Test Build, Buy or Ally",
            "Scan the Field",
            "Read the Candidates",
            "Score the Fit",
            "Pick Who to Approach",
            "Make First Contact",
            "Sign Mutual Confidentiality",
            "Trade the Real Numbers",
            "Write the Joint Thesis",
            "Record the Exploration"
          ]
        },
        {
          "process": "ref/prt/structure-an-alliance",
          "activities": [
            "Set What Each Side Must Get"
          ]
        }
      ]
    }
  }
}

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

# alliance-scout

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 five 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/prt/explore-an-alliance`, `ref/prt/structure-an-alliance`. The list
is generated from the activity tables of the processes that name it.

https://agentcatalog.com/abstract-agents/alliance-scout

skills/find-and-score-the-candidates/SKILL.mdScans the field for names, reads what each candidate sells and to whom, scores each one against the stated reason with the criteria and the inputs recorded, and picks who is approached and in what order. Use it when running `ref/prt/explore-an-alliance`.

---
name: find-and-score-the-candidates
description: Scans the field for names, reads what each candidate sells and to whom, scores each one against the stated reason with the criteria and the inputs recorded, and picks who is approached and in what order. Use it when running `ref/prt/explore-an-alliance`.
license: CC-BY-4.0
metadata:
  agent: alliance-scout
  agent-version: "1"
---

# Find and score the candidates

## What it does

Scans the field for names, reads what each candidate sells and to whom,
scores each one against the stated reason with the criteria and the
inputs recorded, and picks who is approached and in what order.

## Where it happens

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

- **Pick Who to Approach**
  - `ref/prt/explore-an-alliance`, activity 6 -
    [Explore an Alliance](../../../../processes/partners/explore-an-alliance.md)
- **Read the Candidates**
  - `ref/prt/explore-an-alliance`, activity 4 -
    [Explore an Alliance](../../../../processes/partners/explore-an-alliance.md)
- **Scan the Field**
  - `ref/prt/explore-an-alliance`, activity 3 -
    [Explore an Alliance](../../../../processes/partners/explore-an-alliance.md)
- **Score the Fit**
  - `ref/prt/explore-an-alliance`, activity 5 -
    [Explore an Alliance](../../../../processes/partners/explore-an-alliance.md)

## What to record

The strategic reason as written before any company was named, dated. The
build, buy or ally comparison and what it concluded. The candidate list
with the source of each name. Per candidate: what they sell and to whom,
the fit score, the criteria it was scored on, and the inputs behind it.
The shortlist with the order of approach and who was to make it. Per
candidate approached: the date, the person who made contact, and the
mutual confidentiality agreement signed before anything beyond public
material was shown. The numbers each side traded and the agreement they
were traded under. The joint thesis at a version. The exploration
record, kept either way, readable by the next run that names the same
candidate.

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/open-a-conversation-under-confidentiality/SKILL.mdCarries the shortlist to first contact by a named person, sees mutual confidentiality signed before either side shows anything beyond public material, and records the numbers the two sides trade and the agreement they were traded under. Use it when running `ref/prt/explore-an-alliance`.

---
name: open-a-conversation-under-confidentiality
description: Carries the shortlist to first contact by a named person, sees mutual confidentiality signed before either side shows anything beyond public material, and records the numbers the two sides trade and the agreement they were traded under. Use it when running `ref/prt/explore-an-alliance`.
license: CC-BY-4.0
metadata:
  agent: alliance-scout
  agent-version: "1"
---

# Open a conversation under confidentiality

## What it does

Carries the shortlist to first contact by a named person, sees mutual
confidentiality signed before either side shows anything beyond public
material, and records the numbers the two sides trade and the agreement
they were traded under.

## Where it happens

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

- **Make First Contact**
  - `ref/prt/explore-an-alliance`, activity 8 -
    [Explore an Alliance](../../../../processes/partners/explore-an-alliance.md)
- **Sign Mutual Confidentiality**
  - `ref/prt/explore-an-alliance`, activity 10 -
    [Explore an Alliance](../../../../processes/partners/explore-an-alliance.md)
- **Trade the Real Numbers**
  - `ref/prt/explore-an-alliance`, activity 11 -
    [Explore an Alliance](../../../../processes/partners/explore-an-alliance.md)

## What to record

The strategic reason as written before any company was named, dated. The
build, buy or ally comparison and what it concluded. The candidate list
with the source of each name. Per candidate: what they sell and to whom,
the fit score, the criteria it was scored on, and the inputs behind it.
The shortlist with the order of approach and who was to make it. Per
candidate approached: the date, the person who made contact, and the
mutual confidentiality agreement signed before anything beyond public
material was shown. The numbers each side traded and the agreement they
were traded under. The joint thesis at a version. The exploration
record, kept either way, readable by the next run that names the same
candidate.

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-exploration/SKILL.mdFiles the run whether it proceeded or stopped, so the next run that names the same candidate can read what was already found. Use it when running `ref/prt/explore-an-alliance`.

---
name: record-the-exploration
description: Files the run whether it proceeded or stopped, so the next run that names the same candidate can read what was already found. Use it when running `ref/prt/explore-an-alliance`.
license: CC-BY-4.0
metadata:
  agent: alliance-scout
  agent-version: "1"
---

# Record the exploration

## What it does

Files the run whether it proceeded or stopped, so the next run that
names the same candidate can read what was already found.

## Where it happens

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

- **Record the Exploration**
  - `ref/prt/explore-an-alliance`, activity 16 -
    [Explore an Alliance](../../../../processes/partners/explore-an-alliance.md)

## What to record

The strategic reason as written before any company was named, dated. The
build, buy or ally comparison and what it concluded. The candidate list
with the source of each name. Per candidate: what they sell and to whom,
the fit score, the criteria it was scored on, and the inputs behind it.
The shortlist with the order of approach and who was to make it. Per
candidate approached: the date, the person who made contact, and the
mutual confidentiality agreement signed before anything beyond public
material was shown. The numbers each side traded and the agreement they
were traded under. The joint thesis at a version. The exploration
record, kept either way, readable by the next run that names the same
candidate.

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/state-the-reason-for-a-run/SKILL.mdWrites down why the company would work with another company at all, before any candidate is named, and tests whether building it or buying it would answer that reason better. Use it when running `ref/prt/explore-an-alliance`.

---
name: state-the-reason-for-a-run
description: Writes down why the company would work with another company at all, before any candidate is named, and tests whether building it or buying it would answer that reason better. Use it when running `ref/prt/explore-an-alliance`.
license: CC-BY-4.0
metadata:
  agent: alliance-scout
  agent-version: "1"
---

# State the reason for a run

## What it does

Writes down why the company would work with another company at all,
before any candidate is named, and tests whether building it or buying
it would answer that reason better. A run that cannot state its reason
does not start.

## Where it happens

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

- **State the Strategic Reason**
  - `ref/prt/explore-an-alliance`, activity 1 -
    [Explore an Alliance](../../../../processes/partners/explore-an-alliance.md)
- **Test Build, Buy or Ally**
  - `ref/prt/explore-an-alliance`, activity 2 -
    [Explore an Alliance](../../../../processes/partners/explore-an-alliance.md)

## What to record

The strategic reason as written before any company was named, dated. The
build, buy or ally comparison and what it concluded. The candidate list
with the source of each name. Per candidate: what they sell and to whom,
the fit score, the criteria it was scored on, and the inputs behind it.
The shortlist with the order of approach and who was to make it. Per
candidate approached: the date, the person who made contact, and the
mutual confidentiality agreement signed before anything beyond public
material was shown. The numbers each side traded and the agreement they
were traded under. The joint thesis at a version. The exploration
record, kept either way, readable by the next run that names the same
candidate.

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/write-what-the-two-sides-agree-on/SKILL.mdEnds the exploration with a joint thesis one page long that both companies would recognize, and says what our own side has to get out of any arrangement, which the shaping that follows works from. Use it when running `ref/prt/explore-an-alliance` and `ref/prt/structure-an-alliance`.

---
name: write-what-the-two-sides-agree-on
description: Ends the exploration with a joint thesis one page long that both companies would recognize, and says what our own side has to get out of any arrangement, which the shaping that follows works from. Use it when running `ref/prt/explore-an-alliance` and `ref/prt/structure-an-alliance`.
license: CC-BY-4.0
metadata:
  agent: alliance-scout
  agent-version: "1"
---

# Write what the two sides agree on

## What it does

Ends the exploration with a joint thesis one page long that both
companies would recognize, and says what our own side has to get out of
any arrangement, which the shaping that follows works from.

## Where it happens

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

- **Set What Each Side Must Get**
  - `ref/prt/structure-an-alliance`, activity 2 -
    [Structure an Alliance](../../../../processes/partners/structure-an-alliance.md)
- **Write the Joint Thesis**
  - `ref/prt/explore-an-alliance`, activity 13 -
    [Explore an Alliance](../../../../processes/partners/explore-an-alliance.md)

## What to record

The strategic reason as written before any company was named, dated. The
build, buy or ally comparison and what it concluded. The candidate list
with the source of each name. Per candidate: what they sell and to whom,
the fit score, the criteria it was scored on, and the inputs behind it.
The shortlist with the order of approach and who was to make it. Per
candidate approached: the date, the person who made contact, and the
mutual confidentiality agreement signed before anything beyond public
material was shown. The numbers each side traded and the agreement they
were traded under. The joint thesis at a version. The exploration
record, kept either way, readable by the next run that names the same
candidate.

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 6 roles, and the access level beside each one is the most the work needs.

strategy-record · writecompany-data-sources · readcrm · readcontract-system · readconfidentiality-register · writepartner-record · 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": {
    "strategy-record": {
      "type": "streamable-http",
      "url": "https://mcp.yourcompany.com/strategy-record"
    },
    "company-data-sources": {
      "type": "streamable-http",
      "url": "https://mcp.yourcompany.com/company-data-sources"
    },
    "crm": {
      "type": "streamable-http",
      "url": "https://mcp.yourcompany.com/crm"
    },
    "contract-system": {
      "type": "streamable-http",
      "url": "https://mcp.yourcompany.com/contract-system"
    },
    "confidentiality-register": {
      "type": "streamable-http",
      "url": "https://mcp.yourcompany.com/confidentiality-register"
    },
    "partner-record": {
      "type": "streamable-http",
      "url": "https://mcp.yourcompany.com/partner-record"
    }
  }
}

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

2 processes, 12 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.

Explore an Allianceref/prt/explore-an-alliance · 16 activities

State the Strategic Reason · Test Build, Buy or Ally · Scan the Field · Read the Candidates · Score the Fit · Pick Who to Approach · Make First Contact · Sign Mutual Confidentiality · Trade the Real Numbers · Write the Joint Thesis · Record the Exploration

Structure an Allianceref/prt/structure-an-alliance · 16 activities

Set What Each Side Must Get

The records it leaves

What it writes down

The strategic reason as written before any company was named, dated. The build, buy or ally comparison and what it concluded. The candidate list with the source of each name. Per candidate: what they sell and to whom, the fit score, the criteria it was scored on, and the inputs behind it. The shortlist with the order of approach and who was to make it. Per candidate approached: the date, the person who made contact, and the mutual confidentiality agreement signed before anything beyond public material was shown. The numbers each side traded and the agreement they were traded under. The joint thesis at a version. The exploration record, kept either way, readable by the next run that names the same candidate.

Where it stops

What it will not do

Does not run the diligence on a candidate, which is the diligence-coordinator agent, and does not model what the arrangement would be worth or shape its terms, which is the deal-structurer agent. Does not check for contract, customer and rival conflicts itself, which is the supplier-check agent with the legal reviewer (person). Does not negotiate and does not sign. Does not recruit a reseller into a channel programme, which is the partner-manager agent's ground; this agent looks for a strategic fit, not a route to market that already exists.

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: alliance-scout 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.

Scout Security MCP server · varpost.github.io · run it yourself · mirrored from the MCP registry Deterministic, zero-token security scanner your AI agent calls to find and re-verify issues.
naming-signal MCP server · namingsignal.com · hosted · run it yourself · mirrored from the MCP registry Evidence-first naming: briefs, sprints, exact domain checks, finalist research. Read-only.
MVR API - Minimum Viable Relationships MCP server · africanmarketos591.github.io · hosted · mirrored from the MCP registry Read-only MVR preflight for trust, permission, evidence gaps, and African market-entry readiness.