agentleFS
loganware05loganware05/captains-compass-cursor/.cursor/skills/bounded-autonomy/SKILL.md

bounded-autonomy

Skill2 starsChanged 32 days agoMITView on GitHub

Applies Captain-approved routing weight proposals under autonomy budget (Level 3 bounded)

The file

Files
SKILL.md

Bounded Autonomy

Use this Skill when

The Captain has reviewed an experience-routing proposal and wants to apply matcher weight suggestions under an autonomy budget (Milestone 4 Level 3).

Inputs

  • Routing proposal JSON under .agent/routing/proposals/ with captain_approved: true (Captain sets this flag explicitly)
  • Autonomy budget ledger path (recommended)

Procedure

  1. Generate or locate a proposal (experience-routing Skill). Confirm auto_apply remains false.
  2. Captain edits the proposal to set "captain_approved": true.
  3. Apply once under budget:

    ./scripts/apply-routing-proposal.sh \
      --proposal .agent/routing/proposals/<id>.json \
      --budget .agent/budgets/<plan-id>.md

    NorthStar connected routine may surface pending proposals after REVIEW_READY (--surface-routing) but never applies weights from plan approval alone. See Skill northstar-connected-routine.

  4. Context selection apply (M17 — which plan slices appear):

    ./scripts/propose-context-selection.sh --experiences tests/fixtures/experience/contact-counter.json
    # Captain sets captain_approved: true on the context-selection proposal
    ./scripts/apply-context-selection-proposal.sh \
      --proposal .agent/routing/proposals/<ctxsel-id>.json \
      --budget .agent/budgets/<plan-id>.md
  5. Review audit under .agent/routing/applied/ and re-run evals.
  6. Rollback if needed by restoring orchestrator/matcher/weights.json defaults (or rollback/pre-m4-persistent-roles-bounded-autonomy).

Output

  • Updated orchestrator/matcher/weights.json
  • Audit record under .agent/routing/applied/
  • Incremented weight-apply counter on the budget ledger

Prohibited actions

  • Applying without captain_approved: true
  • Auto-applying from proposal generation
  • Mutating Skills or .cursor/agents/ from this Skill
  • Exceeding the plan's maximum weight-apply operations

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.