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 ardev-lab/fake-star-audit --skill skillgit clone --depth 1 https://github.com/ardev-lab/fake-star-auditWrote 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/ardev-lab/fake-star-audit/skill)<a href="https://agentmods.dev/skills/ardev-lab/fake-star-audit/skill"><img src="https://agentmods.dev/badge/skills/ardev-lab/fake-star-audit/skill.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 | $0.00077 | $0.00719 |
| Opus 5 | $0.00039 | $0.00360 |
| Sonnet 5 | $0.00015 | $0.00144 |
| Haiku 4.5 | $0.00008 | $0.00072 |
Grade A, and why
fake-star-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 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 — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
This skill audits a GitHub repository's stargazers for signs of fake-star
injection and returns an explainable risk verdict. It wraps audit.py, a
single-file, zero-dependency, anonymous-API tool (no token, no file writes).
When to use
Trigger when the user asks anything like:
- "is
owner/repofake-starred?" / "are these stars real?" - "check the star authenticity of this GitHub repo"
- "this repo has 5k stars but looks sketchy — verify it"
How to run
audit.py lives at the repository root (one directory above this skill). Run:
python3 /path/to/fake-star-audit/audit.py --repo <owner>/<name> --json
- Requires only Python 3.10+ and outbound HTTPS to
api.github.com. - Uses the anonymous GitHub API (60 req/h). Each audit costs 3–4 requests.
- If you only have the owner/name from a URL like
https://github.com/a/b, pass--repo a/b.
How to interpret the JSON
Key fields:
risk_verdict:LOW/MEDIUM/HIGH.axes: the 5 detection axes, each withflag(bool) andevidence(string, annotated by which window —earliest= bootstrap window,latest= recent drip).extended_signals: booleans likefork_star_inverted,single_repo_mass_injection,trusted_org_parasitism(any hard one forces HIGH).warnings: caveats (e.g. repo too large to page to newest stars).
Verdict logic: HIGH = 3+ axes or a hard signal; MEDIUM = 2 axes or 1 axis + a signal; LOW = 0–1 axes and no hard signals. It is conservative by design.
How to respond to the user
Give a short, plain-language summary, then the reason:
HIGH risk. 100 stars landed in the first 33 minutes after the repo was created, with near-sequential account IDs — a bootstrap-injection pattern, not organic growth.
Always cite the specific flagged axes / evidence. If the verdict is LOW, say so plainly ("stars look organic on the sampled windows") and mention it's a page-1 sample, not a full-history proof. Never present a verdict as definitive proof of fraud — it's a heuristic signal; point the user to the evidence.
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 · 65 lines · 77 tokens per session scan A 6157a3e85557
fake-star-audit is a skill published in the GitHub repository ardev-lab/fake-star-audit (0 stars, last pushed 3mo ago), licensed MIT. It adds 77 tokens to every session and 719 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…