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 abhisekjha/pith --skill pith-reviewgit clone --depth 1 https://github.com/abhisekjha/pithWrote 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/abhisekjha/pith/pith-review)<a href="https://agentmods.dev/skills/abhisekjha/pith/pith-review"><img src="https://agentmods.dev/badge/skills/abhisekjha/pith/pith-review/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/abhisekjha/pith/pith-review"><img src="https://agentmods.dev/badge/skills/abhisekjha/pith/pith-review.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00037 | $0.00453 |
| Opus 5 | $0.00018 | $0.00227 |
| Sonnet 5 | $0.00007 | $0.00091 |
| Haiku 4.5 | $0.00004 | $0.00045 |
Grade A, and why
pith-review 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 12d 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
One line per issue. Exact format:
L<line>: <SEVERITY> <what is wrong>. Fix: <exact change>.
Severity levels
BUG— incorrect behavior, will break in normal useRISK— correct now but fragile, will break under specific conditionsSEC— security vulnerability (injection, auth bypass, data exposure, etc.)PERF— measurable performance problemNIT— style, naming, minor readability improvementQ— genuine question about intent, not a criticism
Rules
- One line per issue. Hard limit.
- No preamble. No "Overall this looks good." No trailing summary.
- If no issues: single line
No issues found. - File prefix only when reviewing multiple files:
auth.ts L42: BUG ... - Fix must be specific. Not "handle this better" — the actual change.
- SEC issues: describe the attack vector, not just "this is insecure."
Examples
L42: BUG token.exp compared in wrong unit (seconds vs ms). Fix: token.exp * 1000 < Date.now()
L87: SEC /auth endpoint has no rate limiting — brute-force viable. Fix: add express-rate-limit, max 10/min per IP
L103: RISK db.query() not wrapped in try/catch — uncaught rejection crashes server. Fix: wrap, return 500
L118: NIT variable named `data` — too generic. Fix: rename to `userProfile`
L201: Q Why is this cached for 24h? Stale user data seems risky here.
For a file with no path given
Start each line with the line number only: L42: BUG ...
For multiple files
Prefix with filename: routes/auth.ts L42: BUG ...
One-shot. Does not persist.
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.
- 12d ago First seen · 49 lines · 37 tokens per session scan A cd9454aa1bcc
pith-review is a skill published in the GitHub repository abhisekjha/pith (98 stars, last pushed 4mo ago), licensed MIT. It adds 37 tokens to every session and 453 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
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.…
codeql
Run CodeQL database creation and security queries, add data-extension models, or process CodeQL SARIF. Use when CodeQL is explicitly requested; use security-review for a broader manual security review.
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.
feature-dev
Guide a feature implementation through a structured seven-phase workflow with deep codebase understanding, clarifying questions, parallel architecture design, and quality review. Use this skill when the user asks to build a new feature, add functionality, or wants a methodical approach to implementation rather than…
huggingface-vision-trainer
Train object-detection, image-classification, or SAM segmentation models on Hugging Face Jobs. Use for vision fine-tuning and evaluation; use huggingface-llm-trainer for language models.
code-quality
Agents should invoke this skill for code reviews, linting/formatting setup, maintainability checks, complexity concerns, warning cleanup, coding standards, or quality gates in Rust, TypeScript, Python, shell, and mixed repos.