agentleFS
hushh-labshushh-labs/hushh-research/.agents/skills/mcp-developer-surface/SKILL.md

mcp-developer-surface

Skill40 starsChanged 3 days agoApache-2.0View on GitHub

Use when changing the Hussh MCP developer surface, @hushh/mcp package behavior, developer API docs, or MCP setup guidance.

The file

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 2 are distinctive, and 4 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.

  • 4

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Avoid overlap with backend-api-contracts and security-audit.

    line 12
  2. Distinctive:

    Treat package behavior, developer docs, and setup guidance as one integrated developer surface.

    line 51
  3. Distinctive:

    Keep package scripts and printed config surfaces aligned with the documented contract.

    line 52
  4. Very specific:

    If the request is still broad or ambiguous, route it back to backend.

    line 57
  5. Very specific:

    If the task becomes general API wire-contract work, use backend-api-contracts.

    line 58
  6. Very specific:

    If the task becomes security or consent enforcement work, use security-audit.

    line 59

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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

Hussh MCP Developer Surface Skill

Purpose and Trigger

  • Primary scope: mcp-developer-surface
  • Trigger on Hussh MCP package behavior, developer API docs, MCP setup guidance, or external developer-surface changes.
  • Avoid overlap with backend-api-contracts and security-audit.

Coverage and Ownership

  • Role: spoke
  • Owner family: backend

Owned repo surfaces:

  1. packages/hushh-mcp
  2. consent-protocol/docs/mcp-setup.md
  3. consent-protocol/docs/reference/developer-api.md

Non-owned surfaces:

  1. backend
  2. security-audit
  3. docs-governance

Do Use

  1. @hushh/mcp package changes.
  2. Developer API docs and MCP setup contract updates.
  3. External developer-surface routing between package, docs, and backend behavior.

Do Not Use

  1. Broad backend intake where the correct spoke is still unclear.
  2. Generic backend runtime or route-placement work.
  3. Internal-only trust policy changes without a developer-surface impact.

Read First

  1. packages/hushh-mcp/README.md
  2. consent-protocol/docs/mcp-setup.md
  3. consent-protocol/docs/reference/developer-api.md

Workflow

  1. Treat package behavior, developer docs, and setup guidance as one integrated developer surface.
  2. Keep package scripts and printed config surfaces aligned with the documented contract.
  3. Route consent-scope and trust-enforcement questions to security-audit when those become the core concern.

Handoff Rules

  1. If the request is still broad or ambiguous, route it back to backend.
  2. If the task becomes general API wire-contract work, use backend-api-contracts.
  3. If the task becomes security or consent enforcement work, use security-audit.

Required Checks

cd packages/hushh-mcp && npm run docs:check
cd packages/hushh-mcp && npm run print-config

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.