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.
npx agentmods add skills/jinning6/noosphere/github-actions-public-ci-diagnosticsnpx skills add JinNing6/Noosphere --skill github-actions-public-ci-diagnosticsgit clone --depth 1 https://github.com/JinNing6/NoosphereWrote 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.
[](https://agentmods.dev/skills/jinning6/noosphere/github-actions-public-ci-diagnostics)<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>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.
| Model | Per session | Once 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 |
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.
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
-
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.
-
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}/logsreturns403 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.
- Use public REST endpoints first:
-
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.
- If annotations only say
-
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.exeplusScripts/tool.exeand POSIXbin/pythonplusbin/toolwhen the production code chooses paths byos.name. - Do not treat a Windows-only fixture as proof that Linux CI is broken.
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.
- 6d ago First seen · 53 lines · 63 tokens per session scan A 201e097abe17
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.
Other skills, from other repositories
mcore-create-issue
Investigate a failing GitHub Actions run or job and create a GitHub issue for the failure.
debug-task
Diagnose and fix moon tasks that are broken, misconfigured, or behaving unexpectedly. Use this skill when a moon task is failing, not running, skipped, hanging, producing stale or wrong output, cached when it shouldn't be, re-running every time when it should be cached, or when outputs are empty or missing after a…
github-ci-fix
Fix failing GitHub CI / Actions checks via fixgithubprci and push to the existing PR head, or fix a branch's failing CI via a linked repair worktree.
github-ci-fix
Use when the user asks OpenSRE to fix failing GitHub CI, GitHub Actions checks, failing pull request checks, a broken PR branch, or CI on a named branch such as main.
meta-long-running-build-watchdog
Watches a long-running command via tmux, lets sub-agent diagnose failures and propose a fix, and records the diagnosis to memory. Designed for overnight model fine-tunes, CI image builds, or repeated regression suites that may fail intermittently.
agentsight-bugfix
AgentSight fix issues 流程。了解问题 → 复现验证 → 根因分析 → 编码修复 → 验证修复,五阶段标准化调试迭代循环。确保 AI agent 遵循最小改动、逐轮验证的修复规范。.