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 MSApps-Mobile/claude-plugins --skill github-cli-health-checkgit clone --depth 1 https://github.com/MSApps-Mobile/claude-pluginsWrote 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/msapps-mobile/claude-plugins/github-cli-health-check)<a href="https://agentmods.dev/skills/msapps-mobile/claude-plugins/github-cli-health-check"><img src="https://agentmods.dev/badge/skills/msapps-mobile/claude-plugins/github-cli-health-check/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/msapps-mobile/claude-plugins/github-cli-health-check"><img src="https://agentmods.dev/badge/skills/msapps-mobile/claude-plugins/github-cli-health-check.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 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 137 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 Rogue Agent · line 157 Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.Fix: Prevent the skill from modifying its own code, SKILL.md, or configuration files. Treat skill files as read-only at runtime.
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 | $0.00151 | $0.01949 |
| Opus 5.5 | $0.00060 | $0.00780 |
| Sonnet 5.5 | $0.00030 | $0.00390 |
| Haiku 4.5 | $0.00015 | $0.00195 |
Grade A, and why
github-cli-health-check 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 1mo 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 — 177 lines — stays where its author put it; the contents beside it link to each section on GitHub.
This skill runs on-demand (no automatic schedule). Execute every step autonomously regardless — do not ask questions, and always produce the markdown report even if checks fail. Read-only only: never mutate GitHub state, never echo the raw token.
Two live paths — pick at runtime
This skill runs in one of three contexts. Detect which you're in and use the matching execution path. Both paths are manual-only and redundant — run whichever is convenient; run both if the first looks off.
| Context | Execution path | How to detect |
|---|---|---|
| Routine (Claude Code cloud, on-demand) | Native gh in the cloud |
Running from a Routine session; gh on PATH; cloud-provided GITHUB_TOKEN. |
| Cowork task (Mac, on-demand) | Desktop Commander → Mac gh | mcp__Desktop_Commander__start_process is available. |
| Interactive local session | Whichever gh works |
User is present; try VM Bash first, fall back to DC if proxy blocks it. |
Routines live under plugins/github-cli-health-check/routines/ in this repo —
see routines/README.md for registration. The Routine has its own prompt
file (routines/prompt.md); this SKILL.md is what the Cowork scheduled task
and interactive sessions load.
Known infrastructure block (tracked upstream)
The Cowork sandbox proxy blocks api.github.com (and
raw.githubusercontent.com, release-assets.githubusercontent.com,
codeload.github.com). Signature: 403 X-Proxy-Error: blocked-by-allowlist.
Project-level sandbox.network.allowedDomains has no effect; sudo is
broken; there is no VM-side install that makes gh work in Cowork today.
But git itself works from the VM. Plain git over HTTPS to
github.com is on the allowlist, so git clone, git fetch, git pull,
and git push all succeed directly from the Cowork VM. Only
api.github.com (REST + GraphQL) is blocked. Practical rule:
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.
- 1mo ago First seen · 177 lines · 151 tokens per session scan A 90a8bcdb7b97
github-cli-health-check is a skill published in the GitHub repository MSApps-Mobile/claude-plugins (10 stars, last pushed today), licensed MIT. It adds 151 tokens to every session and 1,949 once invoked, about $0.0006 per session on Opus 5.5. 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.
Other skills, from other repositories
pr-watch
Local PR watcher. Monitors CI status, automatically fixes failing checks by reading failure logs and applying targeted fixes, then optionally merges when all checks pass. Local CLI analog to Claude Code's cloud auto-fix feature.
deploy-steward
Mainline deploy steward. Consumes ready PRs, owns a lease on mainline landing, refreshes PR state, updates stale branches, waits for CI and deploy gates, merges or queues one candidate at a time, and opens repair tasks for failures.
github-issue-triage
Read, analyze, and draft high-signal GitHub issue responses from bounded provider evidence without silently mutating the repository.
github-pr-review
Review one exact GitHub pull-request head from bounded changed-file patches and check evidence, producing source-line findings without posting or claiming tests ran.
commit-push-pr
Use when asked to commit and push a feature branch, with or without a pull request. Its no-PR mode publishes without a PR. Not for a PR body alone: use create-pull-request.
commit
Use when asked to commit changes, create a typed branch, format history for a changelog, or rewrite messages of HEAD or an unpushed range. Not for pushing or a PR: use commit-push-pr.