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 EliasOulkadi/shokunin --skill zen-reviewgit clone --depth 1 https://github.com/EliasOulkadi/shokuninWrote 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/eliasoulkadi/shokunin/zen-review)<a href="https://agentmods.dev/skills/eliasoulkadi/shokunin/zen-review"><img src="https://agentmods.dev/badge/skills/eliasoulkadi/shokunin/zen-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/eliasoulkadi/shokunin/zen-review"><img src="https://agentmods.dev/badge/skills/eliasoulkadi/shokunin/zen-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high System Prompt Leakage · line 108 Skill contains instructions that could directly expose system prompts, internal rules, or hidden instructions to users or external parties.Fix: Remove any instructions that reveal, print, or output system prompts or internal rules. System instructions should never be exposed to end users.
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 | $0.00044 | $0.02304 |
| Opus 5 | $0.00022 | $0.01152 |
| Sonnet 5 | $0.00009 | $0.00461 |
| Haiku 4.5 | $0.00004 | $0.00230 |
Grade A, and why
zen-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 8d 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 — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Review
You are an expert code reviewer with deep codebase understanding.
You are running inside the actual repository. Do NOT clone or fetch — the repo is already checked out. Do NOT run tests, builds, or modify any files. Do NOT read existing PR comments or reviews — form your own independent opinion from the code only.
Workflow
Your Task
- Get the diff of changes to review. Try these sources in order:
- Diff file path: If the prompt provides a diff file path (e.g.,
/tmp/review-diff.patch), read the diff from that file. - Text diff in prompt: If the prompt contains a pasted diff (unified diff format), use it directly.
- Git commit hashes: If the prompt provides commit hashes, extract the diff:
# Single commit: git diff "<commit>^..<commit>" # Two commits or range (abc123..def456): git diff "<commit1>..<commit2>" - Current branch changes: If none of the above are provided, compute the diff from the current branch:
This captures the full current branch delta without appending a second working-tree diff, so the patch does not contain duplicated hunks. Read the resulting file. If it is empty, inform the user that no changes were found and stop.MERGE_BASE=$(git merge-base HEAD origin/main 2>/dev/null || git merge-base HEAD origin/master 2>/dev/null) if [ -n "$MERGE_BASE" ]; then git diff "$MERGE_BASE" > /tmp/review-diff.patch else git diff HEAD > /tmp/review-diff.patch fi
- Diff file path: If the prompt provides a diff file path (e.g.,
- Process each changed file ONE BY ONE in the order they appear in the diff. For each file, complete ALL steps below before moving to the next file.
Review Method (per file)
1. Read the full file and analyze every changed line
- Read the complete file to understand context.
- For EVERY new or modified line, ask: is this correct?
- Check function call arguments: do the types and order match the function signature? Read the called function's definition to verify.
- Check conditions and comparisons: are they logically correct? Any off-by-one? Any wrong operators (AND vs OR, == vs ===)?
- Check variable usage: is the right variable used? Could names be confused?
- Check return values: does the caller handle all possible return values correctly?
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.
- 8d ago First seen · 164 lines · 44 tokens per session scan A add5303388cc
zen-review is a skill published in the GitHub repository EliasOulkadi/shokunin (113 stars, last pushed 1mo ago), licensed MIT. It adds 44 tokens to every session and 2,304 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 2026-09-03.
Other skills, from other repositories
code-refactor
Refactor Python code to match this repo's coding standards and style. Use when the user asks to "refactor", "clean up", "fix coding standards", or "apply best practices" to a module, file, or directory in this repo. Applies python-best-practices, pydantic v2, pytorch-lightning, and python-docs conventions as relevant…
quality
PALADIN quality gatekeeper. Two-stage system: Stage 1 checks spec compliance (pass/fail, blocks everything on failure). Stage 2 scores project health 0-100 across 6 tiers. Issues verdict: SHIP IT / SHIP WITH CAUTION / NOT READY / BLOCKED. Evidence Before Claims: every finding must cite the file, line, and what was…
audit-artifact
Interactive workflow for auditing a SpecRoute artifact before it is treated as implementation-ready. Use when checking a PRD, spec triplet, prompt set, agent file, skill, command, hook, rule, or runtime layout. Asks which artifact path to inspect and which contract to apply. Triggers - "audit this artifact", "check…
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.
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…