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 pr-reviewgit 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/pr-review)<a href="https://agentmods.dev/skills/momentmaker/kaijutsu/pr-review"><img src="https://agentmods.dev/badge/skills/momentmaker/kaijutsu/pr-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/momentmaker/kaijutsu/pr-review"><img src="https://agentmods.dev/badge/skills/momentmaker/kaijutsu/pr-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 | $0.00152 | $0.01982 |
| Opus 5 | $0.00076 | $0.00991 |
| Sonnet 5 | $0.00030 | $0.00396 |
| Haiku 4.5 | $0.00015 | $0.00198 |
Grade A, and why
pr-review scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.
pr-review
Adversarial multi-agent review. The author already saw the obvious. Your job is to surface what they missed by hearing from THREE independent reviewers — each with a different lens — and distilling the conversation.
This skill wraps jutsu swarm pr-review. The orchestration primitive is in the Go CLI; this skill provides the per-agent prompts, the workflow, and the user-facing wrapper.
Layout (rich)
pr-review/
├── SKILL.md (this file — workflow + decision rules)
├── skill.yaml
├── scripts/
│ └── run.sh thin wrapper: shells `jutsu swarm pr-review "$@"`
├── prompts/
│ ├── claude.md "high-level architecture + correctness"
│ ├── codex.md "be brutal on edge cases"
│ ├── antigravity.md "cross-file pattern hunt + consistency"
│ ├── synthesizer.md cluster, dedupe, render markdown
│ └── debate.md Pass-2 critique template
├── references/
│ ├── prompt-design.md why each lens is what it is
│ └── disagreement-rubric.md how to read the disagreement table
└── runbooks/
├── tuning-prompts.md override prompts per repo
└── interpreting-output.md what each section of the comment means
The CLI loads prompts from this skill's prompts/ directory at runtime; if a file is missing it falls back to the built-in default. So authors can override one lens (e.g. add domain-specific rules to antigravity.md) without recompiling jutsu.
How agents collaborate
Three independent passes, one synthesized output:
| Pass | Mode | What runs |
|---|---|---|
| 1 | always | Each agent reviews independently. N model calls. |
| 2 | --full only | Each agent sees others' Pass-1, critiques. N more calls. |
| Synth | always | One agent (default claude) synthesizes into markdown. 1 call. |
| Filter | --strict only | lie-to-them filter trims sycophancy from synthesis. 1 more call. |
Cost math (N=3 agents):
--quick(default): 4 calls--full: 7 calls--full --strict: 8 calls
What ships with it
13 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.
- evals/evals.json 1.8 KB
- prompts/antigravity.md 1.9 KB
- prompts/claude.md 1.5 KB
- prompts/codex.md 1.5 KB
- prompts/debate.md 642 B
- prompts/synthesizer.md 1017 B
- README.md 537 B
- references/disagreement-rubric.md 2.6 KB
- references/prompt-design.md 3.5 KB
- runbooks/interpreting-output.md 3.4 KB
- runbooks/tuning-prompts.md 2.9 KB
- scripts/run.sh 787 B runs code
- skill.yaml 776 B
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.
- 9d ago First seen · 159 lines · 152 tokens per session scan A d0d7e9d18cdc
pr-review is a skill published in the GitHub repository momentmaker/kaijutsu (3 stars, last pushed 2mo ago), licensed MIT. It adds 152 tokens to every session and 1,982 once invoked, about $0.0008 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".
genie-orca-review
Independent, read-only review of a group, a wish, or a PR on Orca — SHIP / FIX-FIRST / BLOCKED with severity-tagged findings. Council and retro are this skill with a different input.