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

hushh-consent-mcp

Skill40 starsChanged 5 days agoApache-2.0View on GitHub

Use when operating the Hussh Consent MCP core lifecycle or campaign compatibility tools: search_user_scopes, request_consent, check_consent_status, get_encrypted_scoped_export, and prepare_campaign_context.

The file

We split this skill into the rules it gives an agent

11 rules. About 0 are common, 6 are distinctive, and 5 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈6

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 5

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use this when the question is about what the connector returns right now, not when changing backend consent logic.

    line 17
  2. Very specific:

    Avoid overlap with backend, mcp-developer-surface, and security-audit.

    line 18
  3. Distinctive:

    Verify the local host config first if the issue smells like a connector startup failure.

    line 58
  4. Distinctive:

    When scope search returns no matches, check at least two environments when available before concluding it is an information issue.

    line 59
  5. Distinctive:

    Default scope search should stay compact and paginated.

    line 64
  6. Distinctive:

    When auditing PKM parity, compare connector output to the backend metadata route and manifest-backed domain truth for the same user before …

    line 65
  7. Distinctive:

    If the connector returns empty in multiple environments, treat that as a valid empty response until proven otherwise.

    line 67
  8. Very specific:

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

    line 71
  9. Very specific:

    If the task becomes package/docs evolution, hand off to mcp-developer-surface.

    line 72
  10. Very specific:

    If the task becomes consent-policy or trust-boundary analysis, hand off to security-audit.

    line 73
  11. Very specific:

    If the task becomes backend API contract work, hand off to backend-api-contracts.

    line 74

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 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 Consent MCP Skill

Purpose and Trigger

  • Primary scope: hushh-consent-mcp-ops
  • Trigger on direct connector tasks against the Hussh Consent MCP surface:
    • search_user_scopes
    • prepare_campaign_context (Hussh ADK compatibility)
    • request_consent
    • check_consent_status
    • get_encrypted_scoped_export
  • Use this when the question is about what the connector returns right now, not when changing backend consent logic.
  • Avoid overlap with backend, mcp-developer-surface, 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. .agents/skills/hushh-consent-mcp

Non-owned surfaces:

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

Do Use

  1. Verifying whether a specific user resolves to any requestable scopes.
  2. Comparing prod vs UAT connector behavior for the same identifier.
  3. Debugging connector startup/config mismatches across Codex, Claude Desktop, or other MCP hosts.
  4. Verifying whether a missing result is a connector/config issue versus an actual empty discovery response.

Do Not Use

  1. Changing consent scope semantics or IAM policy.
  2. Broad backend runtime work outside the MCP connector.
  3. UI-only consent surface work.

Read First

  1. packages/hushh-mcp/README.md
  2. consent-protocol/docs/mcp-setup.md
  3. docs/operations/coding-agent-mcp.md

Workflow

  1. Verify the local host config first if the issue smells like a connector startup failure.
  2. When scope search returns no matches, check at least two environments when available before concluding it is an information issue.
  3. Distinguish clearly between:
    • connector failed to start
    • connector connected but returned an empty scope-search result
    • environment mismatch between local, UAT, and production
  4. Default scope search should stay compact and paginated. Deep leaf-path expansion is debug-only.
  5. When auditing PKM parity, compare connector output to the backend metadata route and manifest-backed domain truth for the same user before concluding discovery is wrong.
  6. Report only the safe structured connector result before inferring causes; never surface identifiers or tokens.
  7. If the connector returns empty in multiple environments, treat that as a valid empty response until proven otherwise.

Handoff Rules

  1. If the request is still broad or ambiguous, route it back to backend.
  2. If the task becomes package/docs evolution, hand off to mcp-developer-surface.
  3. If the task becomes consent-policy or trust-boundary analysis, hand off to security-audit.
  4. If the task becomes backend API contract work, hand off to backend-api-contracts.

Required Checks

python3 .agents/skills/codex-skill-authoring/scripts/skill_lint.py
./bin/hushh agents audit
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.