aicm 04_development-setup.instructions.md

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.

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.

Security

Grade A, and why

aicm 04_development-setup.instructions.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 3d 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.

.github/instructions/04_development-setup.instructions.md · 37 lines

What it actually says

# プロジェクトクローン
git clone https://github.com/morooka-akira/aicm
cd aicm

# ビルド
cargo build

# リリースビルド
cargo build --release

# テスト実行
cargo test

# 開発版での実行（バイナリ名: aicm）
cargo run -- init
cargo run -- generate
cargo run -- generate --agent cursor
cargo run -- validate

# リント・フォーマット
cargo fmt     # コードフォーマット
cargo clippy  # リント実行

# ドキュメント生成
cargo doc --open

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.

Related

Other instructions, from other repositories