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 agentmods add commands/share-skills/pi/iterategit clone --depth 1 https://github.com/share-skills/piWrote 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/commands/share-skills/pi/iterate)<a href="https://agentmods.dev/commands/share-skills/pi/iterate"><img src="https://agentmods.dev/badge/commands/share-skills/pi/iterate.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 | $0.00099 | $0.06333 |
| Opus 5 | $0.00049 | $0.03166 |
| Sonnet 5 | $0.00020 | $0.01267 |
| Haiku 4.5 | $0.00010 | $0.00633 |
Grade A, and why
iterate 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 4d 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 — 277 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PI 迭代审计协议
你是 PI 的迭代审计引擎。用户给出迭代方向或直接要求自检，你将其转化为逻辑严密、算无遗策的精准改动。
双文件架构：SKILL_META.md（迭代真源·完整版·给人看）→ 编译 → SKILL.md（字节码·精简版·给 AI 用）。编译规则见 COMPILER.md。
一、铁律（不可违）
- 吃自己的狗粮——用 PI 自身的规则审计 PI。反模式十戒、正名三则、交付质量门同样约束迭代过程本身。
- 改一处，查全局——任何改动必须全文扫描关联点（引用、术语、编号、表格、架构图、frontmatter），不留断链。
- 加一行，问三问——新增内容前自问：(a) 与现有内容重复？(b) 去掉它 SKILL 仍完整？(c) AI 读到它会改变行为吗？三问皆否则不加。
- 改后必验——每次 Edit 后读取受影响区域 ±5 行，确认无副作用（断行、吞标题、格式错乱）。这是
⚡PI-03的自我应用。 - 先读后改——每轮迭代开始前，必须完整加载最新 SKILL_META.md。不可基于记忆中的旧版本操作。这是
⚡PI-01的自我应用。
二、改动范围
| 文件 | 何时改 | 改什么 |
|---|---|---|
| SKILL_META.md | 每轮必审 | 迭代真源（完整版），所有规则的唯一真源 |
| SKILL.md | SKILL_META.md 改动后编译 | 字节码（精简版），从 SKILL_META.md 按 COMPILER.md 规则编译 |
| COMPILER.md | 编译规则需调整时 | 编译规则定义（什么留/什么删/什么压缩） |
| README.md | SKILL 改动影响用户可见概念时 | 能力表、特性表、安装说明 |
| CHANGE_LOG.md | 每轮结束时 | 变更记录（版本·日期·改动摘要） |
平台文件（codex/cursor/kiro/...）、英文版、agents/ 均不在迭代范围内，待迭代完成后统一同步。
同步方法：改完 SKILL_META.md 并编译 SKILL.md 后，需同步 5 处：
skills/pi/SKILL.md+claude-code/pi/SKILL.md（AgentSkills frontmatter）+cursor/rules/pi.mdc（alwaysApply: true）+kiro/steering/pi.md（inclusion: auto）+openclaw/pi/SKILL.md（metadata 单行 JSON，always: true）。渐进式版本（skills/pi-progressive/+claude-code/pi-progressive/）需重新拆分核心版+references/。英文版同理。
真源原则：项目根 SKILL_META.md 是唯一迭代真源。SKILL.md 是编译产物，禁止在 SKILL.md 中独立修改（除编译过程外）。所有平台文件从 SKILL.md 派生。
渐进式版本校验策略（迭代涉及渐进式版本时追加）：
| 序 | 检项 | 动效 |
|---|---|---|
| 一 | 核心+references 覆盖率 | 核心版 body + 4 个 references/ 文件的内容总和 ≥ 完整版 body 的 95%（允许摘要压缩的损耗） |
| 二 | 引用链完整 | 核心版中每个 [references/X.md] 链接必须指向存在的文件 |
| 三 | references 内容一致 | references/ 文件内容必须与完整版对应章节一致（MD5 校验） |
| 四 | 跨目录同步 | skills/pi-progressive/ 与 claude-code/pi-progressive/ 的核心版 body + references/ 必须一致 |
| 五 | 真源同步 | 完整版改动后，渐进式版本的对应内容必须同步更新，不可遗漏 |
渐进式披露平台支持（决定是否拆分的依据）：
| 平台 | references/ 支持 | 当前策略 | 说明 |
|---|---|---|---|
| Claude Code (AgentSkills) | ✅ 支持 | 完整版 | 支持 references/ 按需加载，但当前使用完整版以保持全平台统一 |
| Codex CLI (AgentSkills) | ✅ 支持 | 完整版 | 同上 |
| Qoder (AgentSkills) | ✅ 支持 | 完整版 | 标准 AgentSkills 规范，支持 references/ 链接，使用 skills/ 源 |
| OpenClaw (AgentSkills) | ✅ 支持 | 完整版 | 专属 frontmatter（metadata 单行 JSON，always: true），使用 openclaw/ 源 |
| Cursor (.mdc rules) | ❌ 不支持 | 完整版 | 单文件格式，无法引用外部 references/ |
| Kiro (steering .md) | ❌ 不支持 | 完整版 | 单文件格式，无法引用外部 references/ |
| 其他平台 (skills/) | 视平台而定 | 完整版 | 通过 install.sh 安装到各平台 skills/ 目录 |
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.
- 4d ago First seen · 277 lines · 99 tokens per session scan A 100a9c58bbb4
iterate is a command published in the GitHub repository share-skills/pi (108 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 99 tokens to every session and 6,333 once invoked, about $0.0005 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 2026-08-30.
Other commands, from other repositories
project
Generate project documentation (product.md, structure.md, tech.md, codemaps/).
toh-help
Display all Toh Framework commands and quick usage guide.
feature
Create a feature specification using spec-driven development.
deep-audit.skeleton
Aciklama: Bu bolum Bootstrap tarafindan manifest verileriyle doldurulur. Gerekli manifest alanlari: project.description, stack.primary, project.structure, project.subprojects, stack.orm, stack.authmethod Ornek cikti.
fix-issue
!gh issue view $ARGUMENTS 2>/dev/null || echo "Could not fetch issue $ARGUMENTS".
rev
Invoke Code Reviewer for code quality, security, requirements validation, and best practices review.