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 refactor-plangit 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/refactor-plan)<a href="https://agentmods.dev/skills/momentmaker/kaijutsu/refactor-plan"><img src="https://agentmods.dev/badge/skills/momentmaker/kaijutsu/refactor-plan/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/refactor-plan"><img src="https://agentmods.dev/badge/skills/momentmaker/kaijutsu/refactor-plan.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 | $0.00124 | $0.01136 |
| Opus 5.5 | $0.00050 | $0.00454 |
| Sonnet 5.5 | $0.00025 | $0.00227 |
| Haiku 4.5 | $0.00012 | $0.00114 |
Grade A, and why
refactor-plan 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 1mo 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 — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
refactor-plan
Three angles on the same refactor:
| Lens | Agent | Looks for |
|---|---|---|
| Architectural decomposition | claude | The right new shape — abstractions, boundaries, test seams |
| Stepwise risk | codex | Order that minimizes regression — small reversible steps first |
| Pattern consistency | antigravity | Existing repo patterns the refactor should follow, not invent around |
Synthesizer takes all three step proposals, clusters by what-changes, sorts low-risk-first, surfaces ordering disagreements as callouts. Output is an ordered plan with per-step risk + files-touched.
When to invoke
# Single-file refactor
jutsu swarm refactor-plan handlers/users.go --goal "extract auth check into middleware"
# Multi-file (concatenated review — agents reason cross-file)
jutsu swarm refactor-plan cmd/server/handlers.go cmd/server/router.go \
--goal "split monolithic handler module into per-resource services"
# High-stakes — debate + filter
jutsu swarm refactor-plan db/migrations.go --goal "split into per-table migration files" --full --strict
# Iterate on synth prompt without re-spending
jutsu swarm refactor-plan --replay <key>
The --goal flag is REQUIRED. Missing-goal invocation hard-errors with a usage hint. Goal text counts against the 200 KB InputFiles cap (negligible in practice).
First-run consent
Before the first invocation in a repo:
jutsu swarm refactor-plan --grant-consent
Persists allow-multi-model: true to .kaijutsu/refactor-plan.yaml. Files + goal go to remote model providers; explicit consent required.
Reading the output
### Plan
1. **Step 1 — Extract auth check into separate function** (recommended, agreement 3/3)
- What: Move lines 42-58 from handlers/users.go into a new authMiddleware function.
- Why: Single responsibility; isolates auth from request handling.
- Risk: Low. No behavior change. Tests in handlers_test.go cover the path.
- Files touched: handlers/users.go:42-58
2. **Step 2 — Wire middleware into router** (recommended, agreement 2/3)
- ...
### Ordering disagreements
- claude wanted Step 4 before Step 3; codex argued Step 3's reversibility
makes it lower-risk to ship first. Going with codex's order.
### Speculative additions
- Optional: extract a TokenValidator interface for easier mocking.
Defer unless tests need it.
What ships with it
8 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.
- 1mo ago First seen · 98 lines · 124 tokens per session scan A 8db263265da6
refactor-plan is a skill published in the GitHub repository momentmaker/kaijutsu (3 stars, last pushed 8d ago), licensed MIT. It adds 124 tokens to every session and 1,136 once invoked, about $0.0005 per session on Opus 5.5. 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
find-simplifications
Use for a periodic repo-wide sweep of qwen-code for accumulated excess surface — dead components and files, orphaned locale keys, exports nothing consumes, added-then-removed scaffolding — filing candidates on a tracking issue and landing only what a maintainer has said yes to. Repo-wide and evidence-first; every…
swarm-pr-review
Run a graph-guided, tool-augmented PR review using context packing, parallel exploration, mandatory repository-agnostic risk-family coverage with dispatch scaled to diff size and risk, independent reviewer validation, critic challenge, and metrics writeback. Use for deep pull request review with low false-positive…
include-test-files-that-assert-on-behavior-being-changed-in-decl
When delegating a task affected by this skill, include.
code-review
You are a senior code reviewer. You receive diffs via stdin.
review
Adversarial review of an increment before it ships, by a fresh context or another model family; every finding cites path:line and is re-verified. Use for "review", "qa", "critique this".
tech-debt-ci-review
Codex adapter for deep technical-debt and CI-stability audits. Use when asked to find test theater, flaky tests, missing or mis-scoped tests, brittle CI/toolchain behavior, structural debt blocking green PRs, or a remediation order for opencode-swarm.