agentleFS
metagit-aimetagit-ai/metagit-cli/skills/metagit-gating/SKILL.md

metagit-gating

Skill4 starsChanged 12 days agoMITView on GitHub

Use when implementing or operating Metagit MCP server activation and tool exposure rules based on .metagit.yml presence and validity.

The file

We split this skill into the rules it gives an agent

7 rules. About 0 are common, 5 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈5

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use this skill whenever you need to control whether Metagit MCP tools/resources are exposed.

    line 8
  2. Very specific:

    Ensure high-risk tooling and multi-repo context are only available when a valid .metagit.yml exists at the resolved workspace root.

    line 12
  3. Very specific:

    Check for .metagit.yml in resolved root.

    line 42
  4. Distinctive:

    Avoid stack traces in user-facing outputs.

    line 67
  5. Distinctive:

    Never expose mutation-capable tools in inactive state.

    line 72
  6. Distinctive:

    Never operate outside validated workspace boundaries.

    line 73
  7. Distinctive:

    Keep defaults read-only unless user/agent explicitly opts in.

    line 74

≈ “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

Metagit MCP Gating Skill

Use this skill whenever you need to control whether Metagit MCP tools/resources are exposed.

Purpose

Ensure high-risk tooling and multi-repo context are only available when a valid .metagit.yml exists at the resolved workspace root.

Bundled scripts (optional)

Hermes skill_manage installs SKILL.md only. Resolve scripts from the package or a full metagit skills install:

SKILL_ROOT="$(python3 -c "import metagit, pathlib; print(pathlib.Path(metagit.__file__).parent / 'data/skills/metagit-gating')")"
"$SKILL_ROOT/scripts/gate-status.sh" [root_path]

Expected output (single line, tab-delimited):

  • state=<value>\troot=<path|none>\ttools=<count>

Inline CLI fallback (no scripts)

metagit mcp serve --status-once --root .
metagit config validate -c .metagit.yml

Parse mcp_state= from --status-once output (missing, invalid, or active).

Activation Workflow

  1. Resolve workspace root:
    • METAGIT_WORKSPACE_ROOT
    • CLI --root
    • upward directory walk
  2. Check for .metagit.yml in resolved root.
  3. Validate config through existing Metagit config models.
  4. Derive activation state: missing, invalid, or active.
  5. Register tool surface based on state.

Tool Exposure Contract

Inactive (missing or invalid config)

Expose only:

  • metagit_workspace_status
  • metagit_bootstrap_config_plan_only

Active (valid config)

Expose full set:

  • metagit_workspace_status
  • metagit_workspace_index
  • metagit_workspace_search
  • metagit_upstream_hints
  • metagit_repo_inspect
  • metagit_repo_sync
  • metagit_bootstrap_config

Error Handling

  • Return explicit, machine-readable state and reason.
  • Avoid stack traces in user-facing outputs.
  • Log parser/validation errors with enough detail for debugging.

Safety Rules

  • Never expose mutation-capable tools in inactive state.
  • Never operate outside validated workspace boundaries.
  • Keep defaults read-only unless user/agent explicitly opts in.

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.