ThumbGate: Skill for Claude Code

.agents/skills/autonomous-execution-mandate/SKILL.md

autonomous-execution-mandate is a skill for Claude Code from IgorGanapolsky/ThumbGate. It costs 55 tokens per session (549 once invoked), scanned A, original, MIT.

A set of instructions for letting a coding agent continue approved development and release tasks on its own, including monitoring checks and resolving conflicts.

In plain words
What is it for?
Use it for autonomous task chains, CI and Trunk monitoring, targeted fixes, branch and release workflows, and submitting ready pull requests to a merge queue.
Why use it?
It reduces the need to manually prompt the agent after every subtask, test failure, or release step.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: installed under .agents/ (shared by several agents).

This is IgorGanapolsky/ThumbGate's own configuration. It tells Claude Code how to work on ThumbGate itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything ThumbGate configures →

Part of the thumbgate plugin — 37 skills, 7 commands, 1 agent, 5 hooks, 2 MCP servers, 2 plugins shipped together

Reuse

Borrowing it

Nothing to install: this file belongs to IgorGanapolsky/ThumbGate. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/IgorGanapolsky/ThumbGate/main/.agents/skills/autonomous-execution-mandate/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/IgorGanapolsky/ThumbGate

Made for: Claude Code.

Or install thumbgate, the plugin that ships this one along with the rest of its 37 skills, 7 commands, 1 agent, 5 hooks, 2 MCP servers, 2 plugins.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for autonomous-execution-mandate

README.md
[![agentmods](https://agentmods.dev/badge/skills/igorganapolsky/thumbgate/autonomous-execution-mandate/github.svg)](https://agentmods.dev/skills/igorganapolsky/thumbgate/autonomous-execution-mandate)
Your own site
<a href="https://agentmods.dev/skills/igorganapolsky/thumbgate/autonomous-execution-mandate"><img src="https://agentmods.dev/badge/skills/igorganapolsky/thumbgate/autonomous-execution-mandate/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for autonomous-execution-mandate

Your own site · 80×15
<a href="https://agentmods.dev/skills/igorganapolsky/thumbgate/autonomous-execution-mandate"><img src="https://agentmods.dev/badge/skills/igorganapolsky/thumbgate/autonomous-execution-mandate.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 55 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 549 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 2 findings, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Excessive Agency · line 15
    Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
    Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
  • medium Excessive Agency · line 19
    Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
    Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00055 $0.00549
Opus 5 $0.00028 $0.00275
Sonnet 5 $0.00011 $0.00110
Haiku 4.5 $0.00006 $0.00055

Measured 11d ago against content hash bc7bbeebff3c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

autonomous-execution-mandate scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.agents/skills/autonomous-execution-mandate/SKILL.md · 36 lines

How it starts

The opening of the file, as written. The whole thing — 36 lines — stays where its author put it; the contents beside it link to each section on GitHub.

⚡ 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.

Read the full file on GitHub · 36 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 11d ago First seen · 36 lines · 55 tokens per session scan A bc7bbeebff3c

Subscribe to this mod's changes

autonomous-execution-mandate is a skill published in the GitHub repository IgorGanapolsky/ThumbGate (26 stars, last pushed yesterday), licensed MIT. It adds 55 tokens to every session and 549 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

release-engineering

Plan and verify software releases with versioning, changelogs, release branches, feature flags, canaries, migration gates, rollback, deployment checks, and release readiness. Use when preparing a release, shipping a risky PR, coordinating app/backend/database rollout, recovering from a bad deploy, or defining release…

majiayu000/spellbook · 69 tokens

ship

Verify and publish by pushing, opening a PR, and watching CI; land mode merges then cleans branches. Triggers "ship it", "create PR", "/ship", "watch the PR", "babysit CI"; land mode "land it", "/ship land", "fix CI and merge".

darkroomengineering/cc-settings · 63 tokens

checking-release-readiness

Records a ship, block, defer, or ship-with-risk decision that ties baseline, evidence status, residual risk, rollback, monitoring, and handoff together. Use when a packet, PR, release, dependency change, or agent-authority change approaches merge. Do not use early in development before evidence exists.

FlyFission/nuclear-grade-context-engineering · 67 tokens

creating-change-records

Creates or updates Quick or Standard change records, adds the required files, and refreshes what each claim must prove for an evidence-backed pull request. Use when starting or revising a change record. Do not use for a one-off throwaway script, or for work that belongs in an existing record rather than a new one.

FlyFission/nuclear-grade-context-engineering · 70 tokens

land-and-deploy

Merge PR, wait for CI, verify deploy, run canary. The complete landing pipeline.

FlorianBruniaux/claude-code-plugins · 24 tokens

ci-pipeline

Push current branch and return the pipeline tracking URL (GitLab or GitHub Actions).

FlorianBruniaux/claude-code-plugins · 21 tokens