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/msaad00/agent-bom/claude-mdgit clone --depth 1 https://github.com/msaad00/agent-bomWrote 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/instructions/msaad00/agent-bom/claude-md)<a href="https://agentmods.dev/instructions/msaad00/agent-bom/claude-md"><img src="https://agentmods.dev/badge/instructions/msaad00/agent-bom/claude-md.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 | $0.00411 | $0.00411 |
| Opus 5 | $0.00205 | $0.00205 |
| Sonnet 5 | $0.00082 | $0.00082 |
| Haiku 4.5 | $0.00041 | $0.00041 |
Grade A, and why
agent-bom 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 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.
What it actually says
Claude-specific addendum
This file carries Claude-only behavior. Cross-agent project rules live in
AGENTS.md (read by every coding agent that follows the
agents.md convention — Claude, Codex, Cursor, Continue,
Aider, Windsurf).
Read AGENTS.md first. Everything below adds Claude-specific notes that the
agents.md spec doesn't cover.
Memory
- Claude Code auto-loads
MEMORY.mdfrom the per-project memory directory (managed by Claude — not in this repo). Treat it as authoritative for audit history, current release state, and positioning context. - Save new memories after every merge, tag, release, audit, or new user feedback. Don't wait to be asked.
- When saving a date in a memory, write it absolute (
2026-03-05), not relative ("Thursday"). Memory is read later in a different context. - Before recommending a file, function, or flag from memory, verify it still exists in the current code. Stale memory should be updated, not acted on.
Tools
- Use the
Skilltool to invoke registered skills the user typed as/<name>. Never invent skill names. - Use
Agent(subagent) when a task is open-ended, requires many tool calls, or would burn the main context. UseExplorefor read-only searches. - For background long-running commands (server boot, watch scripts), use
Bash run_in_background: trueand rely on the harness notification — do not poll with sleep loops.
Communication
- One-sentence preface before the first tool call in a turn; short updates only at finding / direction-change / blocker moments. End-of-turn summary is one or two sentences.
- For exploratory questions, give a 2-3 sentence recommendation + the main tradeoff before implementing.
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 · 40 lines · 411 tokens per session scan A c3b1d52725dc
agent-bom CLAUDE.md is an instructions file published in the GitHub repository msaad00/agent-bom (31 stars, last pushed today), licensed Apache-2.0. It adds 411 tokens to every session, about $0.0021 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 instructions, from other repositories
vespertide AGENTS.md
AGENTS.md instructions for dev-five-git/vespertide, covering vespertide knowledge base, structure, where to look, data flow and conventions.
mcp-structured-memory CLAUDE.md
Claude Code instructions for nmeierpolys/mcp-structured-memory, a project described as: Structured Memory MCP Server.
inkwell-memory CLAUDE.md
Instructions for veronchenko/inkwell-memory, covering claude.md — inkwellmemory, layout, multi-tenant mode (inkwellmultitenant=1), conventions and testing.
llm-safe-haven CLAUDE.md
Claude Code instructions for pleasedodisturb/llm-safe-haven, covering llm safe haven, what this is, project structure, tdd — non-negotiable (adopted 2026-08-17) and the contract.
cordon AGENTS.md
AGENTS.md instructions for ilyautov/cordon, covering working in this repository, the three invariants, the map, commands and tests.
RNR-Enhanced-Cognee AGENTS.md
AGENTS.md instructions for vincentspereira/RNR-Enhanced-Cognee, covering rnr enhanced cognee implementation for codex, critical requirements, 1. ascii-only output (no unicode encoding), 2. dynamic categories (no hardcoded categories) and 3. standard memory mcp interface.