agentleFS
Sign inStart free
IgorGanapolskyIgorGanapolsky/ThumbGate/.agents/skills/autonomous-execution-mandate/SKILL.md

autonomous-execution-mandate

Skill29 starsChanged 7 months agoMITView on GitHub

Self-directed autonomous execution mandate and workflow skill for ThumbGate agents. Enforces zero-human-intervention task chaining, proactive CI/Trunk monitoring, automated conflict resolution, and evidence-first reporting without requiring manual prompt nudges from the user.

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 1 is distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    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:

    Proactive Remediation: If a test or CI check fails, immediately fetch the raw error logs, apply targeted fixes, and verify locally before …

    line 16
  2. Very specific:

    Submit Green PRs Autonomously: When all required CI checks pass, submit the PR to the Trunk merge queue via node scripts/pr-manager.js …

    line 19
  3. Very specific:

    Evidence Required: Never claim a PR is merged or production is updated without verifying mergedAt timestamp, merge commit SHA, and GET …

    line 24

≈ “Common” is an estimate: at least 1 in 5 of the 308,232 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

⚡ Autonomous Execution Mandate & Workflow Skill

This skill enforces autonomous, self-directed operation across all coding tasks, branch management, and release workflows.

🎯 Core Execution Principles

1. Autonomous Task Chaining (Zero Nudging)

  • Do Not Ask Permission for Sub-Steps: Once an overarching objective is approved, autonomously execute all necessary sub-tasks (inspecting logs, fixing errors, running tests, committing, rebasing, and pushing).
  • Proactive Remediation: If a test or CI check fails, immediately fetch the raw error logs, apply targeted fixes, and verify locally before reporting.

2. Autonomous PR & Merge Lifecycle

  • Submit Green PRs Autonomously: When all required CI checks pass, submit the PR to the Trunk merge queue via node scripts/pr-manager.js <PR_NUM> (or /trunk merge) without asking the user to trigger it.
  • Submit and return (Trunk contract): After a successful queue submission, report the queued state with PR number + head SHA and exit. Do not long-poll the Trunk queue, wait for the final merge commit, or hold the agent session until terminal completion. Re-check asynchronously on the next turn/session only if the operator asks for status or hygiene.
  • Continuous Monitoring (non-Trunk work only): Silently monitor local background tasks (tests, builds) until terminal completion. Trunk merge queue completion is asynchronous and out-of-band.

3. Strict Non-Overclaim Verification

  • Evidence Required: Never claim a PR is merged or production is updated without verifying mergedAt timestamp, merge commit SHA, and GET /health build SHA.
  • Factual Reporting: State exact queue status (e.g. Trunk Merge Candidate PR #3266 CI Pending) rather than claiming completion prematurely.

🛠️ Autonomous Execution Checklist

  • Inspect open PRs, worktrees, and origin/main CI status.
  • Rebase feature branches on origin/main when outdated.
  • Run full test suite (npm test) in clean worktree environment.
  • Submit green PRs to Trunk merge queue (node scripts/pr-manager.js <PR_NUM>).
  • Verify production health endpoint after deployment.

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