What is agent47 CLAUDE.md?

Repository instructions for AgentGuard, whose public code includes a zero-dependency Python safety SDK and a read-only MCP server.

Guiding coding agents through AgentGuard changes while preserving its free MIT SDK, runtime safety focus, repository boundaries, and required definition of done.

They define which files to read, what belongs in the repository, and which product or business areas are outside its scope.

How bmdhodl/agent47 configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to bmdhodl/agent47. 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/bmdhodl/agent47/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/bmdhodl/agent47

Made for: Claude Code.

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/instructions/bmdhodl/agent47/claude-md/github.svg)](https://agentmods.dev/instructions/bmdhodl/agent47/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/bmdhodl/agent47/claude-md"><img src="https://agentmods.dev/badge/instructions/bmdhodl/agent47/claude-md/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/instructions/bmdhodl/agent47/claude-md"><img src="https://agentmods.dev/badge/instructions/bmdhodl/agent47/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,515 This file is loaded in full into every session.

When invoked 1,515 The same file — it is already loaded in full.

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	$0.01515	$0.01515
Opus 5.5	$0.00606	$0.00606
Sonnet 5.5	$0.00303	$0.00303
Haiku 4.5	$0.00152	$0.00152

Measured 16d ago against content hash b1df297ce137, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

agent47 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 16d 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 · 171 lines

How it starts

The opening of the file, as written. The whole thing — 171 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

Shared human-facing design

Before changing any human-facing surface, read DESIGN.md and follow the shared-design instructions in AGENTS.md, including artifact drift checks and separate rendered-surface acceptance.

Claude Code already injects broad tool, style, memory, and session guidance. This file is only for AgentGuard-specific repo rules that Claude would not know otherwise.

Read First

Before touching code or docs, read these files in this order:

memory/state.md
memory/blockers.md
memory/decisions.md
memory/distribution.md
ops/00-NORTHSTAR.md
ops/03-ROADMAP_NOW_NEXT_LATER.md
ops/04-DEFINITION_OF_DONE.md
ARCHITECTURE.md

If memory/ conflicts with older repo docs, memory/ wins.

Repo Boundary

AgentGuard is the public SDK wedge.

sdk/ = zero-dependency Python runtime guardrails SDK
mcp-server/ = narrow read-only MCP surface
hosted dashboard = private repo, out of scope here

Non-negotiable:

SDK stays free, MIT, and zero-dependency
distribution beats random feature expansion
focus stays on runtime enforcement + coding-agent safety
do not add paid/dashboard features in this repo
do not put business-sensitive plans or outreach data in this repo

Claude Repo Contract

Before coding, explicitly restate:

goal
scope
non-goals
done criteria tied to ops/04-DEFINITION_OF_DONE.md

If ops/03-ROADMAP_NOW_NEXT_LATER.md is older than 5 days or ARCHITECTURE.md is older than 14 days, warn before starting work.

Always:

read before editing
keep changes minimal and product-facing
stop if the request conflicts with memory/ or ops/
leave proof for every PR
open every PR ready for review; never create a draft
do the post-PR review loop: CI, automated review, comment sweep, fixes, rerun
address and resolve every comment: reply on the thread, fix or cite the SHA, resolve the GitHub conversation, and repeat until none remain

What Claude Should Optimize For Here

Read the full file on GitHub · 171 lines

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.

16d ago Changed · +6 lines · +44 tokens per session b1df297ce137
1mo ago Changed · -3 tokens per session 11d9d54879c1
1mo ago Changed 4ce9c514b091
1mo ago Changed · +2 lines · +45 tokens per session 19f8e02de79c
1mo ago Changed · +1 lines · +13 tokens per session 3f0c6c275d01
1mo ago Changed · +2 lines · +35 tokens per session f65c1cbac2f0
1mo ago Changed f56055c6a2fb
1mo ago Changed 8b6d8ce63f64
1mo ago Changed · +7 lines · +98 tokens per session 2e2d4976317e
2mo ago First seen · 153 lines · 1,283 tokens per session scan A 34763bd2280d

Subscribe to this mod's changes

agent47 CLAUDE.md is an instructions file published in the GitHub repository bmdhodl/agent47 (4 stars, last pushed 2d ago), licensed MIT. It adds 1,515 tokens to every session, about $0.0061 per session on Opus 5.5. 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.

AI Safety Guardrails LangChain ai-agents anthropic developer-tools

agent47 CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
agent47 CLAUDE.mdbmdhodl/agent47	Instructions file	4	2d ago	MIT	A	1,515	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

agent47: Instructions file for Claude Code