github-actions-public-ci-diagnostics

github-actions-public-ci-diagnostics is a skill for Claude Code, Codex from JinNing6/Noosphere. It costs 63 tokens per session (905 once invoked), scanned A, original, Apache-2.0.

Troubleshooting guidance for failed GitHub Actions jobs, GitHub's automated workflows for testing and releasing code, especially when detailed logs are unavailable. It uses public run, job, check, and annotation information to map the failure.

In plain words
What is it for?
Use it to diagnose remote test, release, publishing, or platform-specific failures and to improve sparse failure annotations before changing code.
Why use it?
It helps investigate failures that do not happen locally or only occur on a particular runner such as Linux or Windows. It also avoids guessing when GitHub restricts access to full logs.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

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/jinning6/noosphere/github-actions-public-ci-diagnostics
Any agent
npx skills add JinNing6/Noosphere --skill github-actions-public-ci-diagnostics
Clone the repo
git clone --depth 1 https://github.com/JinNing6/Noosphere

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 github-actions-public-ci-diagnostics

README.md
[![agentmods](https://agentmods.dev/badge/skills/jinning6/noosphere/github-actions-public-ci-diagnostics.svg)](https://agentmods.dev/skills/jinning6/noosphere/github-actions-public-ci-diagnostics)
Your own site
<a href="https://agentmods.dev/skills/jinning6/noosphere/github-actions-public-ci-diagnostics"><img src="https://agentmods.dev/badge/skills/jinning6/noosphere/github-actions-public-ci-diagnostics.svg" alt="Measured on agentmods" height="20"></a>
Per session 63 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 905 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 5.1 $0.00063 $0.00905
Opus 5 $0.00032 $0.00452
Sonnet 5 $0.00013 $0.00181
Haiku 4.5 $0.00006 $0.00090

Measured 6d ago against content hash 201e097abe17, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

github-actions-public-ci-diagnostics 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 6d 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.

shared_skills/active/github-actions-public-ci-diagnostics/SKILL.md · 53 lines

How it starts

The opening of the file, as written. The whole thing — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.

GitHub Actions Public CI Diagnostics

Use this when a remote GitHub Actions run fails but local tests pass, full job logs are unavailable, or the failure only appears on ubuntu-latest/matrix runners.

Workflow

  1. Check local rules first

    • Inspect project agent rules before changing files.
    • Run the same local quality gates the workflow claims to run.
    • Keep unrelated dirty files out of staging.
  2. Map the remote failure without secrets

    • Use public REST endpoints first:
      • /repos/{owner}/{repo}/actions/runs?head_sha={sha}
      • /repos/{owner}/{repo}/actions/runs/{run_id}/jobs
      • /repos/{owner}/{repo}/commits/{sha}/check-runs
      • /repos/{owner}/{repo}/check-runs/{check_run_id}/annotations
    • If /actions/jobs/{job_id}/logs returns 403 Must have admin rights to Repository, do not guess from missing logs. Treat it as an observability gap.
    • Record the failing workflow, job, step, Python version, event, ref, and exact annotation text.
  3. Add public failure annotations before blind fixes

    • If annotations only say Process completed with exit code 1, add a small repository script that runs pytest, captures stdout/stderr as UTF-8, prints normal output, and emits a GitHub annotation such as ::error title=pytest failed::... on failure.
    • Use a workspace-local pytest temp dir and disable cache when sandbox or CI permissions may differ, for example python -m pytest -q -p no:cacheprovider --basetemp=.pytest-tmp-ci --tb=short --maxfail=1.
    • Wire both quality and publish workflows through the same helper so tag-push release failures are diagnosable too.
    • Add tests asserting the workflows call the helper and the helper contains annotation and step-summary markers.
  4. Reproduce by failure layer

    • First compare workflow order: install, lint, test, build, metadata, release boundary, publish.
    • If tests pass locally but fail on Linux, inspect OS-specific paths, case sensitivity, executable names, path separators, temp/cache directories, locale/encoding, and Python matrix versions.
    • For venv smoke tests, fixtures must create both Windows Scripts/python.exe plus Scripts/tool.exe and POSIX bin/python plus bin/tool when the production code chooses paths by os.name.
    • Do not treat a Windows-only fixture as proof that Linux CI is broken.

Read the full file on GitHub · 53 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. 6d ago First seen · 53 lines · 63 tokens per session scan A 201e097abe17

Subscribe to this mod's changes

github-actions-public-ci-diagnostics is a skill published in the GitHub repository JinNing6/Noosphere (18 stars, last pushed 6d ago), licensed Apache-2.0. It adds 63 tokens to every session and 905 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