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 instructions/itdojp/ae-framework/agents-mdgit clone --depth 1 https://github.com/itdojp/ae-frameworkWhat 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 | $0.01630 | $0.01630 |
| Opus 5 | $0.00815 | $0.00815 |
| Sonnet 5 | $0.00326 | $0.00326 |
| Haiku 4.5 | $0.00163 | $0.00163 |
Grade A, and why
ae-framework AGENTS.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 yesterday.
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 — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS — ae-framework Router
このファイルは、エージェント作業時の最小ルータです。
詳細手順はドメイン別ドキュメントを参照し、本ファイルへの重複列挙を避けます。
Decision Table
| 依頼タイプ | 最初に読む一次情報 | 実行前の判断ポイント | 結果確認先 |
|---|---|---|---|
| CI失敗の復旧 | docs/ci/ci-troubleshooting-guide.md |
required check か opt-in か | 対象Jobログ / PRコメント |
| PR自動化・レビュー運用 | docs/ci/pr-automation.md |
auto-fix / auto-merge の有効条件 | gate / policy-gate / automationコメント |
| Risk判定・ラベル運用 | policy/risk-policy.yml |
risk:low / risk:high と required labels |
policy-gate サマリ |
| GitHub Actions修正 | .github/workflows/*.yml |
printf運用・権限境界・再現性 |
actionlint / 対象workflow結果 |
| Slash Command運用 | .github/workflows/agent-commands.yml |
受理コマンド・付与ラベルの実装値 | PRコメント / 付与ラベル |
| 形式手法・仕様検証 | docs/quality/formal-runbook.md |
実行対象（TLA+/CSP/Lean/Alloy等）と証跡 | artifacts/formal/* |
| GitHub IssueをCodex CLIで処理 | docs/integrations/CODEX-ISSUE-RUNBOOK.md / docs/spec/context-pack.md / spec/context-pack/boundary-map.json |
Issue本文、target files、validation commandを固定し、Context Pack preflight で矛盾時に停止するか | PR本文 / Context Pack conflict 記録 / review completeness / required checks |
| Context Pack / design SSOT に関わる変更 | docs/spec/context-pack.md / spec/context-pack/boundary-map.json |
要求変更が design SSOT、boundary map、acceptance tests と矛盾しないか | context-pack:validate / context-pack:verify-boundary-map / context-pack:deps |
| Producer outputのartifact接続 | docs/agents/agent-producer-matrix.md / docs/agents/evidence-adapters.md |
producer outputをどのjudgment artifactへ正規化するか | Contract Catalog / schema validation / PR summary |
| Multi-agent / subagent 運用 | docs/agents/multi-agent-safety.md |
repo 共有作業か、専用worktree分離が必要か | git status / git worktree list / 差分確認 |
Invariants（不変条件）
- Required checks の基準は
verify-lite+policy-gate（branch protection 設定を一次情報とする）。 - Riskラベルと判定規則の一次情報は
policy/risk-policy.yml。
risk:highは最小1名の人間Approve、必要に応じて policy label / 追加ゲートを要求する。 - GitHub Actions の出力書き込みは
printfを使用し、$GITHUB_OUTPUT/$GITHUB_ENVへの追記はシェル安全性を維持する。 - 方針は
docs/ci-policy.md、運用はdocs/ci/*を一次情報として参照し、AGENTSに再掲しない。 - subagent は read-only を保証しない。repo コンテキストを与えた時点で変更可能として扱う。
- 本リポジトリでは、subagent を書き込み作業に使用しない。commit / push / PR 作成・更新 / Issue 更新は main agent のみが行う。
- subagent の用途は read-only 調査に限定する。repo に触れさせる場合も、隔離用 worktree を用意したうえで担当範囲を明示する。
- subagent 完了後は
git status --short、git log -1、git diff --statを確認し、想定外変更があれば次の作業へ進まない。 - subagent が無断で commit / push / PR 作成・更新 / Issue 更新を行った場合、その差分は隔離対象として扱い、既定動作は「破棄候補」とする。採用する場合でも main agent が内容を再レビューして明示的に採用判断する。
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.
- yesterday First seen · 69 lines · 1,630 tokens per session scan A 4a9cdbad0477
ae-framework AGENTS.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 1,630 tokens to every session, about $0.0081 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.
Other instructions, from other repositories
openllmetry CLAUDE.md
Instructions for traceloop/openllmetry, covering openllmetry repository guide, repository structure, nx workspace commands, run tests across all packages and run linting across all packages.
openinference AGENTS.md
Instructions for Arize-ai/openinference, covering claude.md, repository overview, repository structure, essential commands by language and python.
clawmetry AGENTS.md
Instructions for vivekchand/clawmetry, covering agents.md — for ai coding agents, quick context, where new code goes (open-core split), the rules that bite and common tasks.
gonzo AGENTS.md
Instructions for control-theory/gonzo: This repo includes a Claude Code plugin with a guided log-analysis skill at skills/gonzo/.
signoz-mcp-server CLAUDE.md
Instructions for SigNoz/signoz-mcp-server, covering claude.md — development conventions, feature planning convention, rules, git & pr and code style.
opentelemetry-agent-skills AGENTS.md
Instructions for ollygarden/opentelemetry-agent-skills, covering agents.md, what this repository is, preferred workflow, running the gates locally and skill constraints.