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 skills add PackmindHub/packmind --skill michel-monitor-pull-request-github-actionsgit clone --depth 1 https://github.com/PackmindHub/packmindWrote 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/packmindhub/packmind/michel-monitor-pull-request-github-actions)<a href="https://agentmods.dev/skills/packmindhub/packmind/michel-monitor-pull-request-github-actions"><img src="https://agentmods.dev/badge/skills/packmindhub/packmind/michel-monitor-pull-request-github-actions/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.
<a href="https://agentmods.dev/skills/packmindhub/packmind/michel-monitor-pull-request-github-actions"><img src="https://agentmods.dev/badge/skills/packmindhub/packmind/michel-monitor-pull-request-github-actions.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 6 findings, up to high
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 →
- high Privilege Escalation · line 48 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- high Tool Misuse · line 127 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- high Tool Misuse · line 127 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- high Prompt Injection · line 134 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
- medium Prompt Injection · line 33 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 66 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
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 | $0.00097 | $0.02478 |
| Opus 5 | $0.00048 | $0.01239 |
| Sonnet 5 | $0.00019 | $0.00496 |
| Haiku 4.5 | $0.00010 | $0.00248 |
Grade A, and why
michel-monitor-pull-request-github-actions 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 — 231 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Monitor a pull request's GitHub Actions CI
Called during one iteration of the CI monitor loop. The harness prompt already contains everything needed to start:
{{CHECKS_JSON}}— snapshot of all check statuses at loop entry{{REASON}}—any_failure,stuck, ornot_triggered{{PR_NUMBER}},{{BRANCH}},{{WORKDIR}},{{ITER}},{{MAX_ITER}}
Decision flow
Read CHECKS_JSON in prompt
→ if REASON == "stuck": document timeout in running comment → done
→ if REASON == "not_triggered": investigate why CI never started, document → done
→ if REASON == "any_failure":
1. Identify failing run(s) via gh run list
2. Fetch failed logs with gh run view --log-failed
3. Match pattern → apply fix locally
4. Commit + push
5. Create or update running comment
(if unfixable: document reason → done, no push)
1. Classify — any_failure vs stuck
The bash outer loop has already classified the state; you are invoked only in these two cases:
{{REASON}} |
Meaning | Action |
|---|---|---|
any_failure |
At least one completed check has conclusion ∈ {failure, timed_out, cancelled, action_required} |
Diagnose and fix (sections 2–3) |
stuck |
A workflow started but has been in-progress for >20 min | Document timeout in running comment (section 5) — no code changes |
not_triggered |
Zero checks ever registered for the whole monitoring window — CI never started | Investigate why (section 5) and document — no code changes |
conclusion values to recognise: success / failure / timed_out / cancelled / action_required / neutral / skipped / stale / null.
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 · 231 lines · 97 tokens per session scan A bc88480a3f7b
michel-monitor-pull-request-github-actions is a skill published in the GitHub repository PackmindHub/packmind (310 stars, last pushed today), licensed Apache-2.0. It adds 97 tokens to every session and 2,478 once invoked, about $0.0005 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 2026-09-03.
Other skills, from other repositories
gsd-audit-fix
Autonomous audit-to-fix pipeline — find issues, classify, fix, test, commit.
resolving-merge-conflicts
Use when a git merge or rebase reports conflicts and the operation is in progress.
pr-fix
Bring a PR to mergeable — fix CI failures, address review comments, and resolve merge conflicts. Runs either from a supplied watcher worklist (delegated mode, one pass) or from its own assessment (direct mode, looping until clear). Use after opening a PR when CI is red, reviewers have left comments, or the branch…
review-change
Review a completed change against its authorizing spec in fresh context — evidence-based checks, severity-ranked findings, and a written verdict for the human's merge decision. Use when a diff needs reviewing before merge, or when add-feature / fix-bug / implement-spec reaches its review gate.
verification-before-completion
Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims.
context-align
Checks AGENTS.md and SKILL.md files against the actual codebase for drift. Surfaces references to packages, directories, commands, or patterns that no longer match reality.