What is takt-optimizer?

A TAKT workflow optimizer that edits workflow configuration and supporting files to reduce prompt cost and simplify execution. TAKT is a tool for running structured AI workflows.

Use it to optimize TAKT pieces and facets, apply findings from TAKT analysis, and generate the revised files.

It helps identify ways to use fewer tokens, reuse more rules, simplify control flow, and improve parallel execution while considering quality trade-offs.

How j5ik2o/oni-comb-rs configures Claude Code and Codex

Reuse

Borrowing it

Nothing to install: this file belongs to j5ik2o/oni-comb-rs. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/j5ik2o/oni-comb-rs/main/.agents/skills/takt-optimizer/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/j5ik2o/oni-comb-rs

Made for: Claude Code, Codex.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/j5ik2o/oni-comb-rs/takt-optimizer/github.svg)](https://agentmods.dev/skills/j5ik2o/oni-comb-rs/takt-optimizer)

Your own site

<a href="https://agentmods.dev/skills/j5ik2o/oni-comb-rs/takt-optimizer"><img src="https://agentmods.dev/badge/skills/j5ik2o/oni-comb-rs/takt-optimizer/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/j5ik2o/oni-comb-rs/takt-optimizer"><img src="https://agentmods.dev/badge/skills/j5ik2o/oni-comb-rs/takt-optimizer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 266 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 4,104 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00266	$0.04104
Opus 5	$0.00133	$0.02052
Sonnet 5	$0.00053	$0.00821
Haiku 4.5	$0.00027	$0.00410

Measured 8d ago against content hash 35a98401019c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

takt-optimizer 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.

.agents/skills/takt-optimizer/SKILL.md · 328 lines

How it starts

The opening of the file, as written. The whole thing — 328 lines — stays where its author put it; the contents beside it link to each section on GitHub.

TAKT Optimizer

既存のTAKTワークフローの最適化を実行する。診断・分析は takt-analyze が担う。

前提 takt バージョン: v0.31.0

参照資料

資料	パス	用途
YAMLスキーマ	`references/takt/builtins/skill/references/yaml-schema.md`	ピース構造の検証基準
エンジン仕様	`references/takt/builtins/skill/references/engine.md`	プロンプト構築・トークン消費の理解
スタイルガイド群	`references/takt/builtins/ja/*_STYLE_GUIDE.md`	ファセットサイズ上限
ビルトインピース	`references/takt/builtins/ja/pieces/`	最適化パターンの参照
ビルトインファセット	`references/takt/builtins/ja/facets/{personas,policies,instructions,knowledge,output-contracts}/`	ビルトイン置換候補

takt-analyzeとの違い

観点	takt-analyze	takt-optimize
目的	問題検出・診断とレポート	最適化の実行
出力	分析レポート（Markdown）	最適化済みファイル群
変更	なし（読み取り専用）	ファイルを直接編集・生成
入力	ピースYAML + ファセット + 実行ログ	ピースYAML + ファセット + takt-analyzeの診断結果
判断	問題の重大度分類	コスト/品質のトレードオフ判断
ログ分析	自ら実行し診断レポートを生成	takt-analyzeの診断結果を活用

推奨フロー: takt-analyze（診断）→ その結果をもとに takt-optimize（最適化実行）

最適化カテゴリ

1. トークン消費削減

プロンプト構築時のトークン量を削減する。

エンジンのプロンプト構築順序（参照: engine.md）:

ペルソナ → ポリシー → コンテキスト → ナレッジ → インストラクション
→ タスク → 前回出力 → レポート指示 → タグ指示 → ポリシーリマインダー

注意: ポリシーは冒頭と末尾に2回注入される（Lost in the Middle対策）。ポリシーの肥大化はトークン消費を2倍にする。

最適化	手法	効果
ペルソナ圧縮	冗長な記述の除去、サイズ上限内への圧縮	各ムーブメントで削減
ポリシー分割	巨大ポリシーを用途別に分割し、必要なムーブメントにのみ割り当て	2倍効果（リマインダー分）
ナレッジ絞り込み	ムーブメントに不要なナレッジ参照を除去	不要コンテキスト削減
インストラクション簡素化	自動注入される内容の手動記述を除去	重複排除
出力契約スリム化	30行超の出力契約を圧縮	レポート指示部分で削減

ファセットサイズ目安:

ファセット	推奨	上限
Persona (simple)	30-50行	100行
Persona (expert)	50-300行	550行
Policy	60-250行	300行
Instruction (review)	5-12行	-
Instruction (plan/fix)	10-20行	-
Instruction (implement)	30-50行	-
Output Contract	10-25行	30行

2. ムーブメント統合

不要なムーブメントを統合してワークフロー全体のステップ数を減らす。

パターン	検出条件	最適化
連続する同一ペルソナ	隣接ムーブメントが同じペルソナ	1ムーブメントに統合
単一ルール遷移	ルールが1つで無条件遷移	前後ムーブメントと統合検討
edit=false連鎖	読み取り専用ムーブメントの連鎖	統合可能性を評価

Read the full file on GitHub · 328 lines

Files

What ships with it

60 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.

Changes

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 · 328 lines · 266 tokens per session scan A 35a98401019c

Subscribe to this mod's changes

takt-optimizer is a skill published in the GitHub repository j5ik2o/oni-comb-rs (41 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 266 tokens to every session and 4,104 once invoked, about $0.0013 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 2026-09-01.

Building agents parser

migrate-oxfmt

Guide for migrating a project from Prettier or Biome to Oxfmt. Use when asked to migrate, convert, or switch a JavaScript/TypeScript project's formatter from Prettier or Biome to Oxfmt.

oxc-project/oxc · 53 tokens

migrate-oxlint

Guide for migrating a project from ESLint to Oxlint. Use when asked to migrate, convert, or switch a JavaScript/TypeScript project's linter from ESLint to Oxlint.

oxc-project/oxc · 44 tokens

insta-snapshots

Guide for working with and updating insta snapshot tests in Oxc without terminal interaction.

oxc-project/oxc · 22 tokens

performance-lint-rules

Performance review guidance for Oxc linter rule implementations. Use only when reviewing Rust rule code under crates/oxclinter/src/rules/ or when explicitly auditing those rules for performance improvements.

oxc-project/oxc · 45 tokens

vera-language

Write programs in the Vera programming language. Use when asked to write, edit, debug, or review Vera code (.vera files). Vera is a statically typed, purely functional language with algebraic effects, mandatory contracts, and typed slot references (@T.n) instead of variable names.

aallan/vera · 61 tokens

pcl-expert

Expert in Persona Control Language (PCL) - language design, compiler architecture, runtime systems, and ecosystem development. Use when the user mentions persona control language, compiler design, language design, DSL, runtime systems, or lexer, or when the task involves Language Design & Specification, Compiler…

personamanagmentlayer/pcl · 73 tokens

oni-comb-rs: Skill for Claude Code