agentleFS
Sign inStart free
MicrosoftKnown publishermicrosoft/copilot-agent-inventory-samples/samples/agent-warden/skills/governance-report/SKILL.md

governance-report

Skill29 starsChanged 29 days agoMITView on GitHub

Generate a downloadable governance report of the custom-agent inventory — counts by agent type and owner, currently blocked agents, agents available or deployed to everyone, and potential duplicates — as both a readable Markdown summary and a CSV for further analysis. Use when an admin asks for an inventory summary, a "state of governance" overview, or an exportable report.

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Do not trigger for a single-agent lookup or for taking an action.

    line 13
  2. Distinctive:

    Keep findings as observations.

    line 42

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

governance-report

When to use

Trigger when the admin asks for a summary or export of the inventory, e.g. "give me a governance report", "summarise the agents and export it", "which agents are blocked or shared with everyone — put it in a file".

Do not trigger for a single-agent lookup or for taking an action; those use the existing plugin functions.

Inputs

  • The Agents SharePoint inventory (knowledge source) for the full list: name, Agent Id, agent type, owner, blocked status, availability, deployment, description.
  • The connected Insights Agent for usage and adoption figures (active users, responses sent, last activity) per agent, matched to inventory rows by Agent Id.
  • Optionally the API plugin (warden_GetAgentDetail) to confirm live state for any agent the report flags.

What it does (runs code)

Using the CodeInterpreter capability, build two files from the inventory rows:

  1. governance-report.md — a readable summary with sections:
    • Totals: agent count, grouped by agent type and by owner.
    • Blocked agents (name + Agent Id).
    • Broadly scoped agents where AvailableTo or DeployedTo = all.
    • Potential duplicates: agents sharing a similar name/description/purpose, grouped by theme. When usage data from the Insights Agent is available, classify severity (active vs. dormant) and include active-user/response figures.
  2. governance-report.csv — one row per agent with columns: AgentId, Name, Type, Owner, Blocked, AvailableTo, DeployedTo, ActiveUsers, ResponsesSent, LastActivity for the admin to sort/filter in Excel (usage columns populated from the Insights Agent where available).

Outputs

  • governance-report.md
  • governance-report.csv

Both are for review/download only — producing them takes no governance action.

Notes / constraints

  • Usage and adoption data comes from the connected Insights Agent. Use it to classify duplicate severity and adoption, but do not invent figures where the Insights Agent returns none — mark those as unavailable.
  • Keep findings as observations; recommendations (block / consolidate) are suggestions the admin confirms via the normal write flow.

Status

Draft stub — not yet referenced by the agent.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free