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 code-simplificationgit 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/code-simplification)<a href="https://agentmods.dev/skills/momentmaker/kaijutsu/code-simplification"><img src="https://agentmods.dev/badge/skills/momentmaker/kaijutsu/code-simplification/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/code-simplification"><img src="https://agentmods.dev/badge/skills/momentmaker/kaijutsu/code-simplification.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 | $0.00088 | $0.01081 |
| Opus 5.5 | $0.00035 | $0.00432 |
| Sonnet 5.5 | $0.00018 | $0.00216 |
| Haiku 4.5 | $0.00009 | $0.00108 |
Grade A, and why
code-simplification 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 — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Simplification
Adapted from
addyosmani/agent-skillsunder the MIT License. Copyright (c) Addy Osmani. Modifications by kaijutsu maintainers — composed withpolishandblunder-hunt.
Goal: smaller code, same behavior. The deliverable is a diff that reduces LOC, removes abstractions that earn nothing, and consolidates near-duplicates.
When to invoke
- A file is over 500 lines
- A module's surface has more functions than it has callers per function
- Duplicate logic spotted in 2+ places
- User says "this feels overengineered" or "clean this up"
Process
Step 1: Read before deleting (Chesterton's Fence)
For every candidate removal, ask:
- Why is this here? Find the original commit (
git log -p <file>) and read the message. - Who calls it?
grep -r '<symbol>'or use LSP find-references. - What test covers it?
If you can't answer all three, DO NOT remove it. The fence exists for a reason; first understand the reason, then decide.
Step 2: Find candidates
- Dead code: unreferenced exports, unreachable branches, unused imports
- Duplicate logic: 2+ functions doing the same thing with minor variations
- Premature abstraction: a base class / generic with one concrete subclass / instance
- Leaky helper: a util that exposes implementation details its only caller could inline
- File-over-500: split by cohesion (related functions stay together; orthogonal concerns split out)
Step 3: Apply Rule of 500
If a single file exceeds 500 LOC:
- Identify cohesion clusters within the file
- Split into 2-3 files of <500 LOC each
- Move tests with their code
- Verify imports compile
Step 4: Behavior-preservation gate
After every change:
- Tests still pass
- No public API change (or if there is one, it's marked breaking)
- Diff is reviewable in <10 minutes
If the diff exceeds 500 LOC, you've gone too far — split the simplification into multiple PRs.
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.
- 1mo ago First seen · 97 lines · 88 tokens per session scan A e1ce037403d7
code-simplification is a skill published in the GitHub repository momentmaker/kaijutsu (3 stars, last pushed 8d ago), licensed MIT. It adds 88 tokens to every session and 1,081 once invoked, about $0.0004 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
code_explorer
Explores the repository to locate primary source files, coupled UI components, and test files for bug reports or feature requests.
test-failure-explorer
Import and query an existing Vitest 3.2 JSON report to explore test failures, file-level errors and original diagnostic evidence.
feedback
Skill "feedback" from Hmbown/Codewhale, covering feedback, when to use, setup, workflow and non-goals.
session-investigator
Investigate fast-agent session and history files to diagnose issues. Use when a session ended unexpectedly, when debugging tool loops, when correlating sub-agent traces with main sessions, or when analyzing conversation flow and timing. Covers session.json metadata, history JSON format, message structure, tool…
smiles-validation
Strict SMILES validation, structural comparison, and modification verification. Catches invalid LLM-generated molecules.
oversight-team
Use when you are a seat on the oversight pod (a standing monitor-mode rig that keeps OTHER rigs healthy), configuring or running the drift detectors, or choosing whether to intervene vs escalate. Covers the pull-not-poll posture, the v0 detectors (premature-park, process-drift, off-task, token-burn), the intervention…