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 terrylica/cc-skills --skill health-checkgit clone --depth 1 https://github.com/terrylica/cc-skillsWrote 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/terrylica/cc-skills/health-check)<a href="https://agentmods.dev/skills/terrylica/cc-skills/health-check"><img src="https://agentmods.dev/badge/skills/terrylica/cc-skills/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/terrylica/cc-skills/health-check"><img src="https://agentmods.dev/badge/skills/terrylica/cc-skills/health-check.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00122 | $0.00760 |
| Opus 5 | $0.00061 | $0.00380 |
| Sonnet 5 | $0.00024 | $0.00152 |
| Haiku 4.5 | $0.00012 | $0.00076 |
Grade A, and why
health-check scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.
health-check
Self-Evolving Skill: This skill improves through use. If instructions are wrong, parameters drifted, or a workaround was needed — fix this file immediately, don't defer. Only update for real, reproducible issues.
Self-test + quota for the po plugin, via the TS core.
env -u HTTPS_PROXY -u HTTP_PROXY bun "$(cc-plugin-root pushover-commander)/skills/_lib/pushover_core.ts" doctor # full self-test (JSON)
env -u HTTPS_PROXY -u HTTP_PROXY bun "$(cc-plugin-root pushover-commander)/skills/_lib/pushover_core.ts" quota # {limit, remaining, reset}
doctor checks: creds (op→Keychain), /users/validate.json, monthly quota, the expected custom sounds
(po_fanfare/po_uplift/po_celebrate), deps (bun/uv/Chrome), and the audit log size. quota prints
remaining messages and warns when below quota_warn_remaining (see pushover_api_limits.json).
Reliability primitives (apply to every send)
- Limits SSoT —
skills/_lib/pushover_api_limits.jsonis the single source for all Pushover limits/rules (message 1024, title 250, url 512, attachment 5 MB, sound <500 KB/≤30 s, app name 20, desc 500, html⊕monospace, priority-2 needs retry+expire). Edit there, nowhere else. - Preflight —
pushover_core.tsvalidates every send againstpushover_api_limits.jsonand turns Pushover's silent failures into explicit output: refuses (url>512, attachment>5 MB, html+monospace) — override with--force— and warns (message/title truncation, sound not in account). - Audit trail — every send appends a UUID-keyed JSONL line to
~/.local/state/pushover/po-audit.jsonl(ts, uuid, app, priority, status, request, receipt, remaining, message_len, errors). Retrieve withgrep <uuid> ~/.local/state/pushover/po-audit.jsonl | jq .. - Quota guard — each send reads
X-Limit-App-Remainingand warns when low. - Retry/backoff — transient network / 5xx are retried (×3, backoff) before failing.
Post-Execution Reflection
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.
- 7d ago First seen · 43 lines · 122 tokens per session scan A e941b5e765c1
health-check is a skill published in the GitHub repository terrylica/cc-skills (73 stars, last pushed today), licensed MIT. It adds 122 tokens to every session and 760 once invoked, about $0.0006 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 2026-09-05.
Other skills, from other repositories
debug-systematic
Systematic 4-phase debugging methodology for complex, intermittent, or mysterious issues. Use when investigating bugs, race conditions, or unexplained failures.
backpropagation
Trace runtime bugs back to spec gaps — identify missing acceptance criteria, update specs, generate regression tests, and detect patterns.
evidence-driven-debugging
Use during active debugging when you have a hypothesis to test or need to instrument a running system. Activate for keywords like "debug", "instrument", "log", "trace", "breakpoint", "what's happening at runtime", "production behavior". Pair to investigate-root-cause for the doing-it phase. Always record what you…
investigate-root-cause
Use when encountering ANY bug, error, test failure, or unexpected behavior. Activate for keywords like "bug", "error", "failing", "broken", "doesn't work", "unexpected", "crash", "exception", "TypeError", "undefined", stack traces, or any error message. Also trigger when tests fail unexpectedly, when behavior differs…
map-codebase
Use when entering an unfamiliar codebase or area, before making non-trivial changes, when onboarding to a new system, or when planning a refactor that touches multiple modules. Activate for keywords like "explore", "map", "find where", "trace", "how does X work", "what calls Y", "scope of change". Produces an…
github-actions-silent-failures
Diagnose GitHub Actions workflows that fail silently — a reusable-workflow run that shows zero jobs and no logs (startupfailure), a gh-aw cross-repo import that mis-resolves when the source repo is literally named .github, and self-hosted-runner traps (a shared-tmp race across containers, docker exec landing as an…