fake-star-audit

fake-star-audit is a skill for Claude Code, Codex from ardev-lab/fake-star-audit. It costs 77 tokens per session (719 once invoked), scanned A, original, MIT.

A procedure for checking whether a GitHub repository’s stars look genuine or artificially added. It examines stargazer patterns across five detection areas and returns a LOW, MEDIUM, or HIGH risk verdict with explanations.

In plain words
What is it for?
Use it to audit a repository for possible fake stars, bot activity, or suspicious star-injection patterns.
Why use it?
It helps you assess whether a repository’s star count is trustworthy when its popularity looks unusual.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to audit a repository for possible fake stars, bot activity, or suspicious star-injection patterns.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ardev-lab/fake-star-audit/skill
Install

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.

Any agent
npx skills add ardev-lab/fake-star-audit --skill skill
Clone the repo
git clone --depth 1 https://github.com/ardev-lab/fake-star-audit

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for fake-star-audit

README.md
[![agentmods](https://agentmods.dev/badge/skills/ardev-lab/fake-star-audit/skill.svg)](https://agentmods.dev/skills/ardev-lab/fake-star-audit/skill)
Your own site
<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>
Per session 77 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 719 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 6d ago against content hash 6157a3e85557, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

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.

skill/SKILL.md · 65 lines

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/repo fake-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 with flag (bool) and evidence (string, annotated by which window — earliest = bootstrap window, latest = recent drip).
  • extended_signals: booleans like fork_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.

Read the full file on GitHub · 65 lines

Changes

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.

  1. 6d ago First seen · 65 lines · 77 tokens per session scan A 6157a3e85557

Subscribe to this mod's changes

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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

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…

microsoft/ai-agents-for-beginners · 200 tokens

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…

vercel/next.js · 95 tokens

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…

vercel/next.js · 103 tokens

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…

microsoft/vscode · 72 tokens

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…

openai/codex · 114 tokens