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 momentmaker/kaijutsu --skill polishgit clone --depth 1 https://github.com/momentmaker/kaijutsuWrote 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/momentmaker/kaijutsu/polish)<a href="https://agentmods.dev/skills/momentmaker/kaijutsu/polish"><img src="https://agentmods.dev/badge/skills/momentmaker/kaijutsu/polish.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 | $0.00070 | $0.01406 |
| Opus 5 | $0.00035 | $0.00703 |
| Sonnet 5 | $0.00014 | $0.00281 |
| Haiku 4.5 | $0.00007 | $0.00141 |
Grade A, and why
polish 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 — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.
polish
Loops until clean. Each pass: review the diff, fix everything found, re-run tests/linters. Stop when convergence-detect says no new signal is appearing.
This skill composes:
blunder-huntfor the review (multi-pass adversarial critique)convergence-detectfor the stop condition (smarter than "ran N rounds")verification-before-completionfor the hard test/build/lint gate AFTER convergence (convergence ≠ correctness)deslopfor any user-facing prose touched in the diff
Step 0: Scope
Determine what was implemented:
- Read any active implementation plan if it exists
git diff master...HEAD --stat(or--cached --stat/--statif on master)- Identify all files in the change set
Step 1-N: Review-Fix Passes
Cap at 4 passes. Stop early when convergence-detect says converged.
For each pass, alternate two lenses:
Lens A — Random Code Exploration (odd passes: 1, 3)
Traverse the codebase semi-randomly:
- Pick 5 files in the diff at random
- Read each in full, not just the diff hunks
- Look for: dead code from refactoring, leftover debug statements, missing error handling at system boundaries, security issues, race conditions, missing tests for new paths
- For each finding: severity + file:line + description
Lens B — Cross-Agent Integration Review (even passes: 2, 4)
Look at how pieces fit together:
- List the public-API surface added or changed in the diff
- Find every call site of those APIs (in the diff and outside)
- Verify: contracts honored, error paths handled by callers, no silent type narrowing, no swallowed errors
- For each finding: severity + file:line + description
Apply blunder-hunt to each pass
Run blunder-hunt with the pass's lens on the in-scope files. The primitive handles the lie-to-them pressure and the dedup. Polish just consumes the output.
Parallel pass-runners (when supported)
For a single pass with K lenses, compose dispatch-parallel: spawn one subagent per lens, run all in parallel, collect findings. Wall-time savings are large on big diffs. Each subagent gets the same diff but a different lens prompt; synthesis dedupes findings that surface in 2+ subagents.
What ships with it
2 files 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.
- 8d ago First seen · 120 lines · 70 tokens per session scan A fb6265320c42
polish is a skill published in the GitHub repository momentmaker/kaijutsu (3 stars, last pushed 2mo ago), licensed MIT. It adds 70 tokens to every session and 1,406 once invoked, about $0.0003 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
cn-check
Install and run the Continue CLI (cn) to execute AI agent checks on local code changes. Use when asked to "run checks", "lint with AI", "review my changes with cn", or set up Continue CI locally.
printing-press-output-review
Internal sub-skill: agentic review of a printed CLI's sampled command output for plausibility issues that rule-based checks can't encode (substring-match relevance, format bugs, silent source drops, ranking failures). Invoked via the Skill tool by the main printing-press skill at Phase 4.85 and printing-press-polish…
rework-rate
Measure and interpret PR rework rate — the emerging 5th DORA metric.
review
Validate plans, execution, or PRs against wish criteria — returns SHIP / FIX-FIRST / BLOCKED with severity-tagged gaps.
review
Adversarial fresh-context review of an increment before it ships. Every finding cites path:line and is re-verified. Use when saying "review", "grill this", or "critique the implementation".
architecture
Use when reviewing architecture in any codebase — module boundaries, stated design contracts, abstraction depth, error-handling design. Assess by default, apply changes on request; complexity is dependencies plus obscurity, and deep modules win.