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 wei18/Upkeep --skill upkeep-auditgit clone --depth 1 https://github.com/wei18/UpkeepWrote 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/wei18/upkeep/upkeep-audit)<a href="https://agentmods.dev/skills/wei18/upkeep/upkeep-audit"><img src="https://agentmods.dev/badge/skills/wei18/upkeep/upkeep-audit/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/wei18/upkeep/upkeep-audit"><img src="https://agentmods.dev/badge/skills/wei18/upkeep/upkeep-audit.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 | $0.00040 | $0.00525 |
| Opus 5.5 | $0.00016 | $0.00210 |
| Sonnet 5.5 | $0.00008 | $0.00105 |
| Haiku 4.5 | $0.00004 | $0.00052 |
Grade A, and why
upkeep-audit 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 2mo 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.
What it actually says
Upkeep Local Audit
Run the full Upkeep audit pipeline (discovery → parallel reviewers → synthesis → HTML report) against a local repository. Output-only: the target repo is never modified.
Steps
- Ensure the Upkeep checkout at
~/.cache/upkeep:- Missing:
git clone --depth 1 https://github.com/wei18/upkeep ~/.cache/upkeep - Present:
git -C ~/.cache/upkeep pull --ff-only(if the pull fails — diverged or dirty checkout — delete~/.cache/upkeepand re-clone; it is disposable) - Then
(cd ~/.cache/upkeep && npm ci)after a fresh clone or whenever the pull changedpackage-lock.json(when unsure, run it — it is idempotent).
- Missing:
- Run the audit (takes several minutes; reviewers run as parallel
claude -psubprocesses — run it in the background and report progress):
Pass flags only when the user asked for them, with one exception: the report defaults to~/.cache/upkeep/scripts/local-audit.sh <target-path> [--model M] [--rubric-lang L] [--max-turns N] [--out FILE]./upkeep-report.htmlin the current working directory, so if the working directory is inside the target repo, pass--outpointing outside it (e.g.~/upkeep-report.html) — the audit must never write into the target repo. Other defaults match the CI inputs (claude-opus-4-8, rubricen,30turns);--rubric-langacceptsenorzh-TW. - Summarize: the script prints the report markdown at the end. Present the findings grouped by severity (high → medium → low), each with its file path and a one-line problem statement, then give the absolute path of the generated report file (
upkeep-report.htmlby default, or the--outpath). If any reviewers failed, name them.
Requirements (tell the user what is missing instead of failing silently)
claudeCLI installed and logged in (Claude Pro/Max subscription).- Node 20+, git.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 2mo ago First seen · 27 lines · 40 tokens per session scan A f9679960072a
upkeep-audit is a skill published in the GitHub repository wei18/Upkeep (16 stars, last pushed 4d ago), licensed MIT. It adds 40 tokens to every session and 525 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
merge-batch
Prepare and merge an owner-selected PR batch with contributor credit and exact-candidate admission. Use for a pasted PR list; combined focused validation is diagnostic, and every actual landing still requires its applicable checks and authorization.
make-pr-easy-to-review
Prepare PRs for review by cleaning noisy history, improving PR descriptions, and adding reviewer guidance without changing code behavior. Use for "make this easy to review", "tidy this PR", "clean up commits", or "annotate the diff".
thermo-nuclear-code-quality-review
Run an extremely strict maintainability review for abstraction quality, giant files, and spaghetti-condition growth. Use for a thermo-nuclear code quality review, thermonuclear review, deep code quality audit, or especially harsh maintainability review.
security-review
Perform a focused security review of pending git changes to identify high-confidence security vulnerabilities with real exploitation potential. Use this skill when the user asks for a security review, security audit, vulnerability scan, or wants to check pending changes on a branch for security issues before merging.…
huggingface-llm-trainer
Train or fine-tune language models with TRL or Unsloth on Hugging Face Jobs, including SFT, DPO, GRPO, reward models, and GGUF conversion. Use for cloud LLM training; use huggingface-vision-trainer for vision tasks.
review-work
Post-implementation gate review: run manual QA on the real surface yourself, then launch ONE gate reviewer (never a panel) to audit goal, constraints, code quality, security, missed context, and QA evidence. Use before a PR handoff or when the user explicitly asks to review completed work.