ae-framework CLAUDE.md

A short routing guide for ae-framework, a framework for building and governing agent-based software. It points coding agents to the documents that contain the detailed rules for risks, handoffs, integrations, and multi-agent work.

In plain words
What is it for?
Use it at the start of work to choose the correct project documents, check risk rules, follow handoff procedures, and verify changes against the relevant policies.
Why use it?
It prevents agents from relying on outdated summaries when the authoritative policy or workflow lives elsewhere.

Instructions file

Install

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.

agentmods
npx agentmods add instructions/itdojp/ae-framework/claude-md
Clone the repo
git clone --depth 1 https://github.com/itdojp/ae-framework
Per session 398 This file is loaded in full into every session.
When invoked 398 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.00398 $0.00398
Opus 5 $0.00199 $0.00199
Sonnet 5 $0.00080 $0.00080
Haiku 4.5 $0.00040 $0.00040

Measured 2d ago against content hash d2000b598b8d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ae-framework CLAUDE.md 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 2d 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.

CLAUDE.md · 31 lines

What it actually says

CLAUDE — ae-framework Router

Claude Code 利用時の最小入口です。
詳細手順やポリシー本文は一次情報へ委譲し、このファイルに再掲しません。

Read Order

  1. AGENTS.md — 全エージェント共通の最小ルータ
  2. docs/integrations/CLAUDE-CODE-TASK-TOOL-INTEGRATION.md — Claude Code 向け統合ガイド
  3. docs/agents/README.md — agent 向け索引
  4. docs/agents/handoff.md — AE-HANDOFF プロトコル
  5. policy/risk-policy.yml — risk / label / required gate の SSOT

Role Boundary

  • AGENTS.md: 全エージェント共通の入口
  • CLAUDE.md: Claude Code 固有の入口
  • 詳細な運用・実装値・コマンド列挙は一次情報へ委譲

Invariants

  • risk:high の条件と required labels は policy/risk-policy.yml を優先する
  • handoff は docs/agents/handoff.md の AE-HANDOFF に従う
  • multi-agent / subagent の安全運用は AGENTS.mddocs/agents/multi-agent-safety.md を優先する
  • commit / push / PR / Issue 更新前には対象 workflow / policy / docs の一次情報を確認する

Scope

  • このファイルは Claude Code の「入口」だけを定義する
  • Claude Code 向けの長文説明、実装詳細、サンプルフローは docs/integrations/CLAUDE-CODE-TASK-TOOL-INTEGRATION.md を参照する
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.

  1. 2d ago First seen · 31 lines · 398 tokens per session scan A d2000b598b8d

Subscribe to this mod's changes

ae-framework CLAUDE.md is an instructions file published in the GitHub repository itdojp/ae-framework (2 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 398 tokens to every session, about $0.0020 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 2026-08-31.