A documentation system for keeping an AI-readable project guide in an `AIREADME/` folder. It records the project’s architecture, decisions, setup, and operating rules so agents can understand the repository consistently.

Use it to create, update, or check the project’s AIREADME documents, including for a monorepo—a repository containing multiple apps or packages. It scans the repository and related control files before proposing documentation changes.

It reduces confusion when different agents or projects need to work with the same codebase. It also helps prevent changes that conflict with existing project decisions.

How iyuenan3/worklog-kit configures Codex

Reuse

Borrowing it

Nothing to install: this file belongs to iyuenan3/worklog-kit. 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/iyuenan3/worklog-kit/main/.agents/skills/aireadme/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/iyuenan3/worklog-kit

Made for: 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/iyuenan3/worklog-kit/aireadme/github.svg)](https://agentmods.dev/skills/iyuenan3/worklog-kit/aireadme)

Your own site

<a href="https://agentmods.dev/skills/iyuenan3/worklog-kit/aireadme"><img src="https://agentmods.dev/badge/skills/iyuenan3/worklog-kit/aireadme/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/iyuenan3/worklog-kit/aireadme"><img src="https://agentmods.dev/badge/skills/iyuenan3/worklog-kit/aireadme.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 128 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,082 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	$0.00128	$0.02082
Opus 5	$0.00064	$0.01041
Sonnet 5	$0.00026	$0.00416
Haiku 4.5	$0.00013	$0.00208

Measured 9d ago against content hash 9403489cfd57, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

aireadme 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.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/check.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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/aireadme/SKILL.md · 75 lines

How it starts

The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AIREADME：AI 原生跨项目文档体系

为每个项目维护一个 AIREADME/ 文件夹，作为该项目的 AI 真相源：

跨项目了解：别的项目读 ../<proj>/AIREADME/ 理解本项目的架构、部署和契约。
防偏差：本项目 agent 读 CORE、DECISIONS、ARCHITECTURE，避免实现偏航。

逐文件“写什么 / 不写什么 / 何时更新 / 哪些 N/A”的完整规范在 references/STANDARD.md。执行任何模式前必须完整读取它。

模式

现状 / 触发	模式
项目无 `AIREADME/`	init
已有 `AIREADME/`	update
“检查 / lint”	check

init 流程

先把目标项目根解析为 ROOT=$(git rev-parse --show-toplevel 2>/dev/null || pwd)，后续扫描、创建和检查都锚定 ROOT，不能因为从子目录触发就在子目录新建 AIREADME。再读 references/STANDARD.md，取得 12 文件规范、边界表、项目类型 N/A 矩阵和占位规范。
判项目类型（code / infra / docs·meta / product）。monorepo 仍只在仓库根维护一份 AIREADME；子 app / 包作为组件写入 ARCHITECTURE。
摸清本项目：
- 扫 repo 结构（浅层优先，排除 node_modules/、vendor/、upstream/ 等 vendored 目录）、README.md、docs/ 和已有 PRD / SPEC / INFRA / ROADMAP / OPS / USAGE / ARCHIVE。
- 扫配置与控制面：package.json、Cargo.toml、docker-compose.yml、.env.example、AGENTS.md；若有 CLAUDE.md，把它作为 Claude Code 控制入口一起读。
- 读 git log --oneline -20、git tag 和最新 commit SHA。无任何 commit 时使用 pre-code 哨兵，并遵守 Step 7 的首 commit 保护。
- 可选读取项目记忆，优先级如下：
  1. repo 内更具体的记忆 skill / AGENTS.md 明示的真相源；
  2. 显式配置的 PROJECT_MEMORY_DIR；
  3. $stash 的 canonical 项目记忆目录，可运行 bash ~/.agents/skills/stash/scripts/resolve-memory-dir.sh 定位。历史 Codex 或 Claude memory 不作为自动 fallback。只有用户明确要求迁移或对账时，才把指定历史路径作为只读来源单独检查，不复制、不合并、不软连接到 stash。读取 MEMORY.md 索引和与当前任务相关的条目；不要假设 Codex 会自动注入这些文件。目录不存在是正常情况。
- 若立项时跑过 pm-skills，长稿是临时草稿；按 STANDARD 把结论蒸馏进 CORE + PRD 后即弃，不另建平行文档。
已有文档按内容定归属，不按文件名。重叠内容标记“蒸馏迁入”，例外内容标记“指向 / 保留”，绝不复制。vendored / 上游目录不吸收其 README、AGENTS、CLAUDE、LICENSE；只在 ARCHITECTURE 记录依赖和指针，并清除敏感上游身份。
从 assets/template/AIREADME/ 复制骨架到项目根 AIREADME/，逐文件按 STANDARD 填写：
- 无内容时写语义占位：将放什么、为何空、当前已知状态；不要留裸 TODO。
- 导入即去链：项目内 [[wikilink]] 要迁入内容或改成纯文本；真正的其他项目改为 ../<proj>/AIREADME/；格式占位示例可原样保留。
RELATIONS 的跨项目出向依赖统一指向 ../<proj>/AIREADME/。共享底座写在属主项目根 AIREADME，消费方只指向属主。
把所有破坏性动作合并成一次确认门，等用户确认后才执行：
- 待 git rm 的根文档清单；确认内容已迁妥且 Git 历史可恢复。
- AGENTS.md：若已是薄 router，只提议补维护责任；若臃肿，给 80–150 行 router 的 diff 预览。
- CLAUDE.md：只保留 Claude Code 必需的入口，推荐软链接到共用 router；如果要同步或瘦身，同样给 diff 预览，不自动改。
- 无 commit 项目必须先建立用户确认的 baseline commit，再做 git rm。commit 本身也不自动执行。
写 INDEX 同步锚点：last-synced: <commit SHA> · <date> 独占一行。SHA 表示“最后一次已审阅并被本轮 AIREADME 覆盖的项目内容提交”。实现 / 配置变更应先形成 commit，再用该 HEAD 写锚点；AIREADME 自身随后单独提交，drift 会忽略只改 AIREADME/ 的文档 commit。不要把尚未提交的内容与 AIREADME 混成一个无法自指 SHA 的 commit。唯有确无 commit 才用 pre-code；出现首个真实内容 commit 后，下次 update 必须翻成真 SHA。
运行 scripts/check.sh。🔴 exit 1 必修；🟡 exit 0 是 advisory。报告创建、实填、占位、迁入、指向、待删根、兼容控制面和共享底座处理结果。

Read the full file on GitHub · 75 lines

Files

What ships with it

17 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.

9d ago First seen · 75 lines · 128 tokens per session scan A 9403489cfd57

Subscribe to this mod's changes

aireadme is a skill published in the GitHub repository iyuenan3/worklog-kit (11 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 128 tokens to every session and 2,082 once invoked, about $0.0006 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.

Writing and docs

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

worklog-kit: Skill for Codex