Brand check
brand-check v1Scores material against the standards before people sign it: every claim against the claims register at its version, every asset against the brand guidelines at theirs. This agent is what lets a human sign-off read only the exceptions instead of everything, and it is the usual first agent to climb from supervised to autonomous - one clean run at a time, with the amendment history to show for it.
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.
The examiner in an assessment: the standard is named and versioned before scoring starts, every item gets a verdict, and every verdict cites the rule it was scored against. Its output is the input to the approval that follows.
The plugin
What is in the package
10 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.
brand-check · 15 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 Not a signer. It scores; named people sign. It also does not edit the standards it scores against - the registers and guidelines have their own processes. ## What always goes to a person - everything it fails - this agent never waives its own findings, so every failure goes to a person with the rule and its version named - a claim the register does not cover - a person decides whether the standard gives way or the material does
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 `brand-check` leaves the
following behind, on every run.
A score per item, each citing the standard, its version, and the rule
applied. What passed, what failed, and why, in a form the human signers
read in minutes.
An agent that leaves less than this does not implement `brand-check`,
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
Three 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 |
|---|---|
| brand guidelines | read |
| the claims register | read |
| the asset store | read |
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": "brand-check",
"version": "1.0.0",
"description": "The brand-check abstract agent. Scores material against the standards before people sign it: every claim against the claims register at its version, every asset against the brand guidelines at theirs.",
"author": {
"name": "AgentCatalog",
"url": "https://agentcatalog.com"
},
"homepage": "https://agentcatalog.com/abstract-agents/brand-check",
"repository": "https://github.com/jeffrschneider/agentcatalog",
"license": "CC-BY-4.0",
"keywords": [
"abstract-agent",
"reference",
"marketing",
"brand-guidelines",
"brand-refresh",
"brand-voice",
"abstract"
],
"extensions": {
"com.agentcatalog.agent": {
"agent": "brand-check",
"agentVersion": 1,
"department": "marketing",
"abstract": true,
"works": "The examiner in an assessment: the standard is named and versioned before scoring starts, every item gets a verdict, and every verdict cites the rule it was scored against. Its output is the input to the approval that follows.",
"servers": [
{
"name": "brand guidelines",
"role": "brand-guidelines",
"access": "read"
},
{
"name": "the claims register",
"role": "claims-register",
"access": "read"
},
{
"name": "the asset store",
"role": "asset-store",
"access": "read"
}
],
"records": [
"A score per item, each citing the standard, its version, and the rule applied.",
"What passed, what failed, and why, in a form the human signers read in minutes."
],
"escalates": [
"everything it fails - this agent never waives its own findings, so every failure goes to a person with the rule and its version named",
"a claim the register does not cover - a person decides whether the standard gives way or the material does"
],
"not": [
"Not a signer.",
"It scores; named people sign.",
"It also does not edit the standards it scores against - the registers and guidelines have their own processes."
],
"processes": [
{
"process": "ref/mkt/account-based-play",
"activities": [
"Get Sign-Offs"
]
},
{
"process": "ref/mkt/advisory-board",
"activities": [
"Get Sign-Offs"
]
},
{
"process": "ref/mkt/announce-company-news",
"activities": [
"Get Sign-Offs"
]
},
{
"process": "ref/mkt/approve-marketing-material",
"activities": [
"Score against Brand and Claims"
]
},
{
"process": "ref/mkt/award-entry",
"activities": [
"Get Sign-Offs"
]
},
{
"process": "ref/mkt/brand-audit",
"activities": [
"Brief the Audit",
"Score the Sample"
]
},
{
"process": "ref/mkt/brand-guidelines",
"activities": [
"Read the Guidelines in Force",
"Show the Examples",
"Test the Rules on Real Work",
"List What the New Version Fails"
]
},
{
"process": "ref/mkt/brand-identity",
"activities": [
"Take Stock of the Marks in Use",
"Test the Directions against the Positioning"
]
},
{
"process": "ref/mkt/brand-positioning",
"activities": [
"Audit What the Company Says Now"
]
},
{
"process": "ref/mkt/brand-refresh",
"activities": [
"Score What Is Live against the New Version",
"Get Sign-Offs",
"Sweep for What Was Missed"
]
},
{
"process": "ref/mkt/brand-voice",
"activities": [
"Turn the Voice into Scorable Rules",
"Score Old Material against the Draft Rules",
"Watch How the Rules Score"
]
},
{
"process": "ref/mkt/brief-executive-leadership",
"activities": [
"Get Sign-Offs"
]
},
{
"process": "ref/mkt/brief-industry-analyst",
"activities": [
"Get Sign-Offs"
]
},
{
"process": "ref/mkt/channel-program",
"activities": [
"Get Sign-Offs"
]
},
{
"process": "ref/mkt/churn-risk-play",
"activities": [
"Get Sign-Off"
]
},
{
"process": "ref/mkt/co-marketing-campaign",
"activities": [
"Score against Both Rule Sets"
]
},
{
"process": "ref/mkt/competitive-battlecard",
"activities": [
"Score the Claims"
]
},
{
"process": "ref/mkt/conversion-experiment",
"activities": [
"Get Sign-Offs"
]
},
{
"process": "ref/mkt/creative-assets",
"activities": [
"Score against the Standards",
"Check the Sized Set"
]
},
{
"process": "ref/mkt/crisis-communication",
"activities": [
"Get Sign-Offs"
]
},
{
"process": "ref/mkt/customer-case-study",
"activities": [
"Get Internal Sign-Offs"
]
},
{
"process": "ref/mkt/customer-newsletter",
"activities": [
"Get Sign-Offs"
]
},
{
"process": "ref/mkt/customer-reviews",
"activities": [
"Check the Ask against the Rules"
]
},
{
"process": "ref/mkt/display-retargeting",
"activities": [
"Get Sign-Offs"
]
},
{
"process": "ref/mkt/enable-channel-partner",
"activities": [
"Get Sign-Offs"
]
},
{
"process": "ref/mkt/feature-release",
"activities": [
"Check It Once"
]
},
{
"process": "ref/mkt/field-event",
"activities": [
"Get Sign-Offs"
]
},
{
"process": "ref/mkt/influencer-campaign",
"activities": [
"Review the Drafts"
]
},
{
"process": "ref/mkt/landing-page",
"activities": [
"Score the Page"
]
},
{
"process": "ref/mkt/long-form-content",
"activities": [
"Get Sign-Offs"
]
},
{
"process": "ref/mkt/name-product",
"activities": [
"Screen the Long List"
]
},
{
"process": "ref/mkt/nurture-sequence",
"activities": [
"Score the Messages"
]
},
{
"process": "ref/mkt/onboarding-email-program",
"activities": [
"Check and Sign What Was Made"
]
},
{
"process": "ref/mkt/paid-search-campaign",
"activities": [
"Get Sign-Offs"
]
},
{
"process": "ref/mkt/pitch-earned-media",
"activities": [
"Get Sign-Offs"
]
},
{
"process": "ref/mkt/pricing-change",
"activities": [
"Get Sign-Offs"
]
},
{
"process": "ref/mkt/product-launch",
"activities": [
"Get Sign-Offs"
]
},
{
"process": "ref/mkt/product-positioning",
"activities": [
"Get Sign-Offs"
]
},
{
"process": "ref/mkt/refresh-content",
"activities": [
"Score the Pages against the Current Standards",
"Get Sign-Offs"
]
},
{
"process": "ref/mkt/sales-enablement-kit",
"activities": [
"Score the Kit"
]
},
{
"process": "ref/mkt/social-campaign",
"activities": [
"Get Sign-Offs"
]
},
{
"process": "ref/mkt/speaking-engagement",
"activities": [
"Clear the Proposal",
"Get Sign-Offs"
]
},
{
"process": "ref/mkt/test-ad-creative",
"activities": [
"Get Sign-Offs"
]
},
{
"process": "ref/mkt/trade-show",
"activities": [
"Get Sign-Offs"
]
},
{
"process": "ref/mkt/traffic-ad-creative",
"activities": [
"Score the Adapted Set"
]
},
{
"process": "ref/mkt/user-conference",
"activities": [
"Clear the Speaker Material"
]
},
{
"process": "ref/mkt/video-asset",
"activities": [
"Score against the Standards"
]
},
{
"process": "ref/mkt/webinar",
"activities": [
"Get Sign-Offs"
]
},
{
"process": "ref/mkt/website-content-update",
"activities": [
"Score the Change"
]
},
{
"process": "ref/mkt/win-back-campaign",
"activities": [
"Score the Messages"
]
}
]
}
}
}
README.mdWhat the package is, and why it carries no mcp.json.
# brand-check 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 ten 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/account-based-play`, `ref/mkt/advisory-board`, `ref/mkt/announce-company-news`, `ref/mkt/approve-marketing-material`, `ref/mkt/award-entry`, `ref/mkt/brand-audit`, and 44 more. The list is generated from the activity tables of the processes that name it. https://agentcatalog.com/abstract-agents/brand-check
skills/bring-the-standard-to-a-briefing/SKILL.mdThe agent sits in the briefing that opens an audit and gives everyone the same account of the scope and the standard being applied. Use it when running `ref/mkt/brand-audit`.
--- name: bring-the-standard-to-a-briefing description: The agent sits in the briefing that opens an audit and gives everyone the same account of the scope and the standard being applied. Use it when running `ref/mkt/brand-audit`. license: CC-BY-4.0 metadata: agent: brand-check agent-version: "1" --- # Bring the standard to a briefing ## What it does The agent sits in the briefing that opens an audit and gives everyone the same account of the scope and the standard being applied. ## 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 Audit** - `ref/mkt/brand-audit`, activity 4 - [Conduct Brand Audit](../../../../processes/marketing/brand-audit.md) ## What to record A score per item, each citing the standard, its version, and the rule applied. What passed, what failed, and why, in a form the human signers read in minutes. 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-in-force/SKILL.mdThe agent reads the standards as they stand today and names every rule a proposed change would contradict, at the version each rule is held at. Use it when running `ref/mkt/brand-guidelines`.
--- name: read-the-rules-in-force description: The agent reads the standards as they stand today and names every rule a proposed change would contradict, at the version each rule is held at. Use it when running `ref/mkt/brand-guidelines`. license: CC-BY-4.0 metadata: agent: brand-check agent-version: "1" --- # Read the rules in force ## What it does The agent reads the standards as they stand today and names every rule a proposed change would contradict, at the version each rule is held at. ## 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 Guidelines in Force** - `ref/mkt/brand-guidelines`, activity 2 - [Publish Brand Guidelines](../../../../processes/marketing/brand-guidelines.md) ## What to record A score per item, each citing the standard, its version, and the rule applied. What passed, what failed, and why, in a form the human signers read in minutes. 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-how-the-rules-are-scoring/SKILL.mdThe agent reads the scoring record over time and reports which rules keep failing and which ones nobody ever applies. Use it when running `ref/mkt/brand-voice`.
--- name: report-how-the-rules-are-scoring description: The agent reads the scoring record over time and reports which rules keep failing and which ones nobody ever applies. Use it when running `ref/mkt/brand-voice`. license: CC-BY-4.0 metadata: agent: brand-check agent-version: "1" --- # Report how the rules are scoring ## What it does The agent reads the scoring record over time and reports which rules keep failing and which ones nobody ever applies. ## Where it happens The agent does this in one activity across one reference process. Each one names the activity as that process words it. - **Watch How the Rules Score** - `ref/mkt/brand-voice`, activity 18 - [Define Brand Voice and Messaging](../../../../processes/marketing/brand-voice.md) ## What to record A score per item, each citing the standard, its version, and the rule applied. What passed, what failed, and why, in a form the human signers read in minutes. 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/score-a-candidate-against-the-criteria/SKILL.mdThe agent scores proposed names and design directions against the criteria they have to meet and against what the positioning promises, and says which ones fail and on which criterion. Use it when running `ref/mkt/brand-identity` and `ref/mkt/name-product`.
--- name: score-a-candidate-against-the-criteria description: The agent scores proposed names and design directions against the criteria they have to meet and against what the positioning promises, and says which ones fail and on which criterion. Use it when running `ref/mkt/brand-identity` and `ref/mkt/name-product`. license: CC-BY-4.0 metadata: agent: brand-check agent-version: "1" --- # Score a candidate against the criteria ## What it does The agent scores proposed names and design directions against the criteria they have to meet and against what the positioning promises, and says which ones fail and on which criterion. ## Where it happens The agent does this in two activities across two reference processes. Each one names the activity as that process words it. - **Screen the Long List** - `ref/mkt/name-product`, activity 5 - [Name Product or Company](../../../../processes/marketing/name-product.md) - **Test the Directions against the Positioning** - `ref/mkt/brand-identity`, activity 6 - [Develop Brand Identity](../../../../processes/marketing/brand-identity.md) ## What to record A score per item, each citing the standard, its version, and the rule applied. What passed, what failed, and why, in a form the human signers read in minutes. 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/score-material-before-it-goes-out/SKILL.mdThe agent reads a piece that is about to publish and scores it against the claims register and the guidelines at the versions in force. Use it when running `ref/mkt/approve-marketing-material` and 13 other reference processes.
--- name: score-material-before-it-goes-out description: The agent reads a piece that is about to publish and scores it against the claims register and the guidelines at the versions in force. Use it when running `ref/mkt/approve-marketing-material` and 13 other reference processes. license: CC-BY-4.0 metadata: agent: brand-check agent-version: "1" --- # Score material before it goes out ## What it does The agent reads a piece that is about to publish and scores it against the claims register and the guidelines at the versions in force. It returns a verdict on every rule with the evidence behind it, so a sign-off only has to read the exceptions. ## Where it happens The agent does this in thirteen activities across fourteen reference processes. Each one names the activity as that process words it. - **Check It Once** - `ref/mkt/feature-release`, activity 5 - [Announce Feature Release](../../../../processes/marketing/feature-release.md) - **Check the Ask against the Rules** - `ref/mkt/customer-reviews`, activity 7 - [Solicit Customer Reviews](../../../../processes/marketing/customer-reviews.md) - **Check the Sized Set** - `ref/mkt/creative-assets`, activity 11 - [Produce Creative Assets](../../../../processes/marketing/creative-assets.md) - **Review the Drafts** - `ref/mkt/influencer-campaign`, activity 12 - [Run Influencer Campaign](../../../../processes/marketing/influencer-campaign.md) - **Score against Both Rule Sets** - `ref/mkt/co-marketing-campaign`, activity 7 - [Run Co-Marketing Campaign](../../../../processes/marketing/co-marketing-campaign.md) - **Score against Brand and Claims** - `ref/mkt/approve-marketing-material`, activity 4 - [Approve Marketing Material](../../../../processes/marketing/approve-marketing-material.md) - **Score against the Standards** - `ref/mkt/creative-assets`, activity 8 - [Produce Creative Assets](../../../../processes/marketing/creative-assets.md) - `ref/mkt/video-asset`, activity 11 - [Produce Video Asset](../../../../processes/marketing/video-asset.md) - **Score the Adapted Set** - `ref/mkt/traffic-ad-creative`, activity 7 - [Traffic Ad Creative](../../../../processes/marketing/traffic-ad-creative.md) - **Score the Change** - `ref/mkt/website-content-update`, activity 7 - [Update Website Content](../../../../processes/marketing/website-content-update.md) - **Score the Claims** - `ref/mkt/competitive-battlecard`, activity 10 - [Refresh Competitive Battlecard](../../../../processes/marketing/competitive-battlecard.md) - **Score the Kit** - `ref/mkt/sales-enablement-kit`, activity 10 - [Produce Sales Enablement Kit](../../../../processes/marketing/sales-enablement-kit.md) - **Score the Messages** - `ref/mkt/nurture-sequence`, activity 9 - [Build Nurture Sequence](../../../../processes/marketing/nurture-sequence.md) - `ref/mkt/win-back-campaign`, activity 10 - [Run Win-Back Campaign](../../../../processes/marketing/win-back-campaign.md) - **Score the Page** - `ref/mkt/landing-page`, activity 9 - [Publish Landing Page](../../../../processes/marketing/landing-page.md) ## What to record A score per item, each citing the standard, its version, and the rule applied. What passed, what failed, and why, in a form the human signers read in minutes. 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/score-what-is-already-live/SKILL.mdThe agent reads material that is already published against the standard now in force and lists what fails, including anything still carrying a version that has been replaced. Use it when running `ref/mkt/brand-audit` and 4 other reference processes.
--- name: score-what-is-already-live description: The agent reads material that is already published against the standard now in force and lists what fails, including anything still carrying a version that has been replaced. Use it when running `ref/mkt/brand-audit` and 4 other reference processes. license: CC-BY-4.0 metadata: agent: brand-check agent-version: "1" --- # Score what is already live ## What it does The agent reads material that is already published against the standard now in force and lists what fails, including anything still carrying a version that has been replaced. ## Where it happens The agent does this in six activities across five reference processes. Each one names the activity as that process words it. - **Audit What the Company Says Now** - `ref/mkt/brand-positioning`, activity 4 - [Define Brand Positioning](../../../../processes/marketing/brand-positioning.md) - **List What the New Version Fails** - `ref/mkt/brand-guidelines`, activity 15 - [Publish Brand Guidelines](../../../../processes/marketing/brand-guidelines.md) - **Score What Is Live against the New Version** - `ref/mkt/brand-refresh`, activity 7 - [Roll Out Brand Refresh](../../../../processes/marketing/brand-refresh.md) - **Score the Pages against the Current Standards** - `ref/mkt/refresh-content`, activity 5 - [Refresh Published Content](../../../../processes/marketing/refresh-content.md) - **Score the Sample** - `ref/mkt/brand-audit`, activity 7 - [Conduct Brand Audit](../../../../processes/marketing/brand-audit.md) - **Sweep for What Was Missed** - `ref/mkt/brand-refresh`, activity 22 - [Roll Out Brand Refresh](../../../../processes/marketing/brand-refresh.md) ## What to record A score per item, each citing the standard, its version, and the rule applied. What passed, what failed, and why, in a form the human signers read in minutes. 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-stock-of-the-marks-in-use/SKILL.mdThe agent lists the marks, colors, type and files the organization is using today, before anyone decides what to change. Use it when running `ref/mkt/brand-identity`.
--- name: take-stock-of-the-marks-in-use description: The agent lists the marks, colors, type and files the organization is using today, before anyone decides what to change. Use it when running `ref/mkt/brand-identity`. license: CC-BY-4.0 metadata: agent: brand-check agent-version: "1" --- # Take stock of the marks in use ## What it does The agent lists the marks, colors, type and files the organization is using today, before anyone decides what 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. - **Take Stock of the Marks in Use** - `ref/mkt/brand-identity`, activity 2 - [Develop Brand Identity](../../../../processes/marketing/brand-identity.md) ## What to record A score per item, each citing the standard, its version, and the rule applied. What passed, what failed, and why, in a form the human signers read in minutes. 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-the-material-through-the-sign-off/SKILL.mdThe agent puts the scored material in front of the people who sign, showing them the exceptions and the rule each one failed, and records the signature or the changes that were asked for. Use it when running `ref/mkt/account-based-play` and 29 other reference processes.
--- name: take-the-material-through-the-sign-off description: The agent puts the scored material in front of the people who sign, showing them the exceptions and the rule each one failed, and records the signature or the changes that were asked for. Use it when running `ref/mkt/account-based-play` and 29 other reference processes. license: CC-BY-4.0 metadata: agent: brand-check agent-version: "1" --- # Take the material through the sign off ## What it does The agent puts the scored material in front of the people who sign, showing them the exceptions and the rule each one failed, and records the signature or the changes that were asked for. ## Where it happens The agent does this in six activities across 30 reference processes. Each one names the activity as that process words it. - **Check and Sign What Was Made** - `ref/mkt/onboarding-email-program`, activity 7 - [Run Onboarding Email Program](../../../../processes/marketing/onboarding-email-program.md) - **Clear the Proposal** - `ref/mkt/speaking-engagement`, activity 4 - [Secure Speaking Engagement](../../../../processes/marketing/speaking-engagement.md) - **Clear the Speaker Material** - `ref/mkt/user-conference`, activity 6 - [Host User Conference](../../../../processes/marketing/user-conference.md) - **Get Internal Sign-Offs** - `ref/mkt/customer-case-study`, activity 14 - [Produce Customer Case Study](../../../../processes/marketing/customer-case-study.md) - **Get Sign-Off** - `ref/mkt/churn-risk-play`, activity 7 - [Run Churn-Risk Play](../../../../processes/marketing/churn-risk-play.md) - **Get Sign-Offs** - `ref/mkt/account-based-play`, activity 10 - [Run Account-Based Play](../../../../processes/marketing/account-based-play.md) - `ref/mkt/advisory-board`, activity 8 - [Convene Customer Advisory Board](../../../../processes/marketing/advisory-board.md) - `ref/mkt/announce-company-news`, activity 10 - [Announce Company News](../../../../processes/marketing/announce-company-news.md) - `ref/mkt/award-entry`, activity 11 - [Submit Award Entry](../../../../processes/marketing/award-entry.md) - `ref/mkt/brand-refresh`, activity 16 - [Roll Out Brand Refresh](../../../../processes/marketing/brand-refresh.md) - `ref/mkt/brief-executive-leadership`, activity 13 - [Brief Executive Leadership](../../../../processes/marketing/brief-executive-leadership.md) - `ref/mkt/brief-industry-analyst`, activity 8 - [Brief Industry Analyst](../../../../processes/marketing/brief-industry-analyst.md) - `ref/mkt/channel-program`, activity 10 - [Launch Channel Program](../../../../processes/marketing/channel-program.md) - `ref/mkt/conversion-experiment`, activity 9 - [Run Conversion Experiment](../../../../processes/marketing/conversion-experiment.md) - `ref/mkt/crisis-communication`, activity 8 - [Manage Crisis Communication](../../../../processes/marketing/crisis-communication.md) - `ref/mkt/customer-newsletter`, activity 12 - [Publish Customer Newsletter](../../../../processes/marketing/customer-newsletter.md) - `ref/mkt/display-retargeting`, activity 10 - [Run Display Retargeting Campaign](../../../../processes/marketing/display-retargeting.md) - `ref/mkt/enable-channel-partner`, activity 8 - [Enable Channel Partner](../../../../processes/marketing/enable-channel-partner.md) - `ref/mkt/field-event`, activity 7 - [Host Field Event](../../../../processes/marketing/field-event.md) - `ref/mkt/long-form-content`, activity 10 - [Produce Long-Form Content](../../../../processes/marketing/long-form-content.md) - `ref/mkt/paid-search-campaign`, activity 7 - [Run Paid Search Campaign](../../../../processes/marketing/paid-search-campaign.md) - `ref/mkt/pitch-earned-media`, activity 7 - [Pitch Earned Media](../../../../processes/marketing/pitch-earned-media.md) - `ref/mkt/pricing-change`, activity 8 - [Launch Pricing Change](../../../../processes/marketing/pricing-change.md) - `ref/mkt/product-launch`, activity 7 - [Launch Product](../../../../processes/marketing/product-launch.md) - `ref/mkt/product-positioning`, activity 14 - [Develop Product Positioning](../../../../processes/marketing/product-positioning.md) - `ref/mkt/refresh-content`, activity 15 - [Refresh Published Content](../../../../processes/marketing/refresh-content.md) - `ref/mkt/social-campaign`, activity 6 - [Run Social Media Campaign](../../../../processes/marketing/social-campaign.md) - `ref/mkt/speaking-engagement`, activity 9 - [Secure Speaking Engagement](../../../../processes/marketing/speaking-engagement.md) - `ref/mkt/test-ad-creative`, activity 10 - [Test Ad Creative](../../../../processes/marketing/test-ad-creative.md) - `ref/mkt/trade-show`, activity 7 - [Exhibit at Trade Show](../../../../processes/marketing/trade-show.md) - `ref/mkt/webinar`, activity 6 - [Produce Webinar](../../../../processes/marketing/webinar.md) ## What to record A score per item, each citing the standard, its version, and the rule applied. What passed, what failed, and why, in a form the human signers read in minutes. 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/try-draft-rules-on-real-work/SKILL.mdThe agent scores existing work against rules that have not issued yet, so the people writing those rules can see what the rules would do before they take effect. Use it when running `ref/mkt/brand-guidelines` and `ref/mkt/brand-voice`.
--- name: try-draft-rules-on-real-work description: The agent scores existing work against rules that have not issued yet, so the people writing those rules can see what the rules would do before they take effect. Use it when running `ref/mkt/brand-guidelines` and `ref/mkt/brand-voice`. license: CC-BY-4.0 metadata: agent: brand-check agent-version: "1" --- # Try draft rules on real work ## What it does The agent scores existing work against rules that have not issued yet, so the people writing those rules can see what the rules would do before they take effect. ## Where it happens The agent does this in two activities across two reference processes. Each one names the activity as that process words it. - **Score Old Material against the Draft Rules** - `ref/mkt/brand-voice`, activity 12 - [Define Brand Voice and Messaging](../../../../processes/marketing/brand-voice.md) - **Test the Rules on Real Work** - `ref/mkt/brand-guidelines`, activity 10 - [Publish Brand Guidelines](../../../../processes/marketing/brand-guidelines.md) ## What to record A score per item, each citing the standard, its version, and the rule applied. What passed, what failed, and why, in a form the human signers read in minutes. 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-rules-that-can-be-scored/SKILL.mdThe agent turns a standard into numbered rules that can be applied the same way every time, each one carrying a passing and a failing example taken from real material. Use it when running `ref/mkt/brand-guidelines` and `ref/mkt/brand-voice`.
--- name: write-rules-that-can-be-scored description: The agent turns a standard into numbered rules that can be applied the same way every time, each one carrying a passing and a failing example taken from real material. Use it when running `ref/mkt/brand-guidelines` and `ref/mkt/brand-voice`. license: CC-BY-4.0 metadata: agent: brand-check agent-version: "1" --- # Write rules that can be scored ## What it does The agent turns a standard into numbered rules that can be applied the same way every time, each one carrying a passing and a failing example taken from real material. ## Where it happens The agent does this in two activities across two reference processes. Each one names the activity as that process words it. - **Show the Examples** - `ref/mkt/brand-guidelines`, activity 7 - [Publish Brand Guidelines](../../../../processes/marketing/brand-guidelines.md) - **Turn the Voice into Scorable Rules** - `ref/mkt/brand-voice`, activity 11 - [Define Brand Voice and Messaging](../../../../processes/marketing/brand-voice.md) ## What to record A score per item, each citing the standard, its version, and the rule applied. What passed, what failed, and why, in a form the human signers read in minutes. 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 3 roles, and the access level beside each one is the most the work needs.
brand-guidelines · readclaims-register · readasset-store · read
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": {
"brand-guidelines": {
"type": "streamable-http",
"url": "https://mcp.yourcompany.com/brand-guidelines"
},
"claims-register": {
"type": "streamable-http",
"url": "https://mcp.yourcompany.com/claims-register"
},
"asset-store": {
"type": "streamable-http",
"url": "https://mcp.yourcompany.com/asset-store"
}
}
}
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
50 processes, 62 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.
Run Account-Based Playref/mkt/account-based-play · 19 activities
Get Sign-Offs
Convene Customer Advisory Boardref/mkt/advisory-board · 16 activities
Get Sign-Offs
Announce Company Newsref/mkt/announce-company-news · 17 activities
Get Sign-Offs
Approve Marketing Materialref/mkt/approve-marketing-material · 13 activities
Score against Brand and Claims
Submit Award Entryref/mkt/award-entry · 16 activities
Get Sign-Offs
Conduct Brand Auditref/mkt/brand-audit · 17 activities
Brief the Audit · Score the Sample
Publish Brand Guidelinesref/mkt/brand-guidelines · 16 activities
Read the Guidelines in Force · Show the Examples · Test the Rules on Real Work · List What the New Version Fails
Develop Brand Identityref/mkt/brand-identity · 16 activities
Take Stock of the Marks in Use · Test the Directions against the Positioning
Define Brand Positioningref/mkt/brand-positioning · 16 activities
Audit What the Company Says Now
Roll Out Brand Refreshref/mkt/brand-refresh · 26 activities
Score What Is Live against the New Version · Get Sign-Offs · Sweep for What Was Missed
Define Brand Voice and Messagingref/mkt/brand-voice · 19 activities
Turn the Voice into Scorable Rules · Score Old Material against the Draft Rules · Watch How the Rules Score
Brief Executive Leadershipref/mkt/brief-executive-leadership · 20 activities
Get Sign-Offs
Brief Industry Analystref/mkt/brief-industry-analyst · 17 activities
Get Sign-Offs
Launch Channel Programref/mkt/channel-program · 17 activities
Get Sign-Offs
Run Churn-Risk Playref/mkt/churn-risk-play · 12 activities
Get Sign-Off
Run Co-Marketing Campaignref/mkt/co-marketing-campaign · 16 activities
Score against Both Rule Sets
Refresh Competitive Battlecardref/mkt/competitive-battlecard · 16 activities
Score the Claims
Run Conversion Experimentref/mkt/conversion-experiment · 16 activities
Get Sign-Offs
Produce Creative Assetsref/mkt/creative-assets · 12 activities
Score against the Standards · Check the Sized Set
Manage Crisis Communicationref/mkt/crisis-communication · 16 activities
Get Sign-Offs
Produce Customer Case Studyref/mkt/customer-case-study · 21 activities
Get Internal Sign-Offs
Publish Customer Newsletterref/mkt/customer-newsletter · 17 activities
Get Sign-Offs
Solicit Customer Reviewsref/mkt/customer-reviews · 16 activities
Check the Ask against the Rules
Run Display Retargeting Campaignref/mkt/display-retargeting · 16 activities
Get Sign-Offs
Enable Channel Partnerref/mkt/enable-channel-partner · 16 activities
Get Sign-Offs
Announce Feature Releaseref/mkt/feature-release · 10 activities
Check It Once
Host Field Eventref/mkt/field-event · 16 activities
Get Sign-Offs
Run Influencer Campaignref/mkt/influencer-campaign · 16 activities
Review the Drafts
Publish Landing Pageref/mkt/landing-page · 15 activities
Score the Page
Produce Long-Form Contentref/mkt/long-form-content · 18 activities
Get Sign-Offs
Name Product or Companyref/mkt/name-product · 16 activities
Screen the Long List
Build Nurture Sequenceref/mkt/nurture-sequence · 16 activities
Score the Messages
Run Onboarding Email Programref/mkt/onboarding-email-program · 14 activities
Check and Sign What Was Made
Run Paid Search Campaignref/mkt/paid-search-campaign · 13 activities
Get Sign-Offs
Pitch Earned Mediaref/mkt/pitch-earned-media · 15 activities
Get Sign-Offs
Launch Pricing Changeref/mkt/pricing-change · 16 activities
Get Sign-Offs
Launch Productref/mkt/product-launch · 11 activities
Get Sign-Offs
Develop Product Positioningref/mkt/product-positioning · 17 activities
Get Sign-Offs
Refresh Published Contentref/mkt/refresh-content · 22 activities
Score the Pages against the Current Standards · Get Sign-Offs
Produce Sales Enablement Kitref/mkt/sales-enablement-kit · 16 activities
Score the Kit
Run Social Media Campaignref/mkt/social-campaign · 13 activities
Get Sign-Offs
Secure Speaking Engagementref/mkt/speaking-engagement · 16 activities
Clear the Proposal · Get Sign-Offs
Test Ad Creativeref/mkt/test-ad-creative · 18 activities
Get Sign-Offs
Exhibit at Trade Showref/mkt/trade-show · 16 activities
Get Sign-Offs
Traffic Ad Creativeref/mkt/traffic-ad-creative · 17 activities
Score the Adapted Set
Host User Conferenceref/mkt/user-conference · 17 activities
Clear the Speaker Material
Produce Video Assetref/mkt/video-asset · 15 activities
Score against the Standards
Produce Webinarref/mkt/webinar · 18 activities
Get Sign-Offs
Update Website Contentref/mkt/website-content-update · 12 activities
Score the Change
Run Win-Back Campaignref/mkt/win-back-campaign · 20 activities
Score the Messages
The records it leaves
What it writes down
A score per item, each citing the standard, its version, and the rule applied. What passed, what failed, and why, in a form the human signers read in minutes.
Where it stops
What it will not do
Not a signer. It scores; named people sign. It also does not edit the standards it scores against - the registers and guidelines have their own processes.
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: brand-check 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.
- ShipCheck MCP server · wtaylorwilson.github.io · hosted · mirrored from the MCP registry Independent preview-URL QA for coding agents. Playwright heuristics, pass/fail pack.
- proof MCP server · toremlabs.github.io · run it yourself · mirrored from the MCP registry Govern your AI coding agent: frame the work, review the changes, keep a signed decision record.
- rigour MCP server · rigour-labs.github.io · run it yourself · mirrored from the MCP registry Quality gates for AI agents. Lint, test, build checks with memory persistence.