execute-github-action

execute-github-action is a skill for Claude Code, Codex from joy7758/titmas-agent-action-gate. It costs 25 tokens per session (287 once invoked), scanned A, original, Apache-2.0.

An experimental step for performing one precisely approved GitHub action and recording the attempt. GitHub is a code-hosting service where repositories and pull requests are managed.

In plain words
What is it for?
Use it to carry out one allowed GitHub provider call, such as a repository operation, and retain its signed decision binding, response details, and follow-up evidence.
Why use it?
It limits execution to the exact action, target, and parameters approved by the gate, while preserving both success and failure evidence.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/joy7758/titmas-agent-action-gate/execute-github-action
Any agent
npx skills add joy7758/titmas-agent-action-gate --skill execute-github-action
Clone the repo
git clone --depth 1 https://github.com/joy7758/titmas-agent-action-gate

Made for: Claude Code, Codex.

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 execute-github-action

README.md
[![agentmods](https://agentmods.dev/badge/skills/joy7758/titmas-agent-action-gate/execute-github-action.svg)](https://agentmods.dev/skills/joy7758/titmas-agent-action-gate/execute-github-action)
Your own site
<a href="https://agentmods.dev/skills/joy7758/titmas-agent-action-gate/execute-github-action"><img src="https://agentmods.dev/badge/skills/joy7758/titmas-agent-action-gate/execute-github-action.svg" alt="Measured on agentmods" height="20"></a>
Per session 25 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 287 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00025 $0.00287
Opus 5 $0.00013 $0.00143
Sonnet 5 $0.00005 $0.00057
Haiku 4.5 $0.00003 $0.00029

Measured 3d ago against content hash f3d5ebcb1e9f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

execute-github-action 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 3d 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.

skills/execute-github-action/SKILL.md · 32 lines

What it actually says

Execute exact GitHub action

Status: EXPERIMENTAL_REFERENCE_IMPLEMENTATION_NO_AUTONOMOUS_AGENT_AUTHORITY.

Inputs

  • server-side decision reference, never model-pasted decision content;
  • exact provider action, target, parameters, and idempotency key;
  • provider identity and ACL managed outside prompts.

Output

One append-only execution-attempt receipt including provider response data, timestamps, bound decision ID, and redacted metadata.

Required procedure

  1. Fetch and verify signature, expiry, outcome, exact binding, and unconsumed state.
  2. Atomically consume the decision for one attempt.
  3. Invoke only the bound allowlisted provider tool.
  4. Capture success or failure without secrets.
  5. Generate post-execution evidence for independent verification.

Stop conditions

Stop on any mismatch, replay, expiry, unavailable gate, provider ACL failure, parameter expansion, or request to merge/tag/release under a PR-create decision. The manifest keeps may_execute=false because the Worker has no autonomous authority; the separate service/provider boundary consumes a valid decision and provider ACL for one attempt.

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 3d ago First seen · 32 lines · 25 tokens per session scan A f3d5ebcb1e9f

Subscribe to this mod's changes

execute-github-action is a skill published in the GitHub repository joy7758/titmas-agent-action-gate (0 stars, last pushed 11d ago), licensed Apache-2.0. It adds 25 tokens to every session and 287 once invoked, about $0.0001 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 2026-08-31.

Related

Other skills, from other repositories

multi-agent-governance

Use this skill when building, managing, or auditing multi-agent AI systems. Provides governance patterns for behavioral enforcement, drift detection, audit trails, role management, and accountability across autonomous AI agents. Compatible with any orchestration framework.

levelsofself/mcp-nervous-system · 51 tokens

pull-request-review

Use for a GitHub pull request review run to inspect the exact head revision, changed files, and checks, then publish one evidence-backed managed review comment without approving or modifying the pull request.

wellkilo/RepoPilot · 42 tokens

repository-triage

Use when a new GitHub issue or failed workflow enters RepoPilot and you must classify, deduplicate, assess risk, define acceptance criteria, and produce an execution DAG before delegating work.

wellkilo/RepoPilot · 43 tokens

runbook-archival

Use after verification to convert a completed or failed maintenance run into a deduplicated, reusable Runbook linked to evidence and the exact repository revision.

wellkilo/RepoPilot · 35 tokens

root-cause-localization

Use after triage to reproduce a repository failure, locate the smallest supported root cause, analyze impact, and return evidence without changing files.

wellkilo/RepoPilot · 33 tokens

safe-patch-authoring

Use only after a root cause is evidenced to create the smallest patch, focused tests, a dedicated branch and commit, and optionally a pull request under the pullrequestonly policy.

wellkilo/RepoPilot · 41 tokens