Borrowing it
Nothing to install: this file belongs to skynetcmd/m3-memory. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/skynetcmd/m3-memory/main/CLAUDE.mdgit clone --depth 1 https://github.com/skynetcmd/m3-memoryWrote 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/skynetcmd/m3-memory/claude-md)<a href="https://agentmods.dev/instructions/skynetcmd/m3-memory/claude-md"><img src="https://agentmods.dev/badge/instructions/skynetcmd/m3-memory/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.
<a href="https://agentmods.dev/instructions/skynetcmd/m3-memory/claude-md"><img src="https://agentmods.dev/badge/instructions/skynetcmd/m3-memory/claude-md.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.01901 | $0.01901 |
| Opus 5.5 | $0.00760 | $0.00760 |
| Sonnet 5.5 | $0.00380 | $0.00380 |
| Haiku 4.5 | $0.00190 | $0.00190 |
Grade D, and why
m3-memory CLAUDE.md scanned grade D with 2 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.
Hidden instructionshighPrompt injection
Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.
<!-- `docs/AGENT_INSTRUCTIONS.md` is PUBLISHED MATERIAL FOR ADOPTERS: a menu of agent-setup guidance for people installing m3, to cut and choose from. It is NOT instructions for the agent working in this repo, and it is Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
`~/.claude/settings.json` (only `~/.claude.json`, `.mcp.json`, and plugins are How it starts
The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Git Standards
-
Commit Messages: Do NOT include "Co-Authored-By" lines in commit messages. Focus on clear, concise descriptions of "why" and "what".
-
Pre-push process (MANDATORY, all agents): After cloning, run
python bin/setup_hooks.pyonce to enable the shared pre-push gate. Before any push, the tool-catalog drift check (python bin/check_tool_catalog_drift.py) and bench-data leakage scan must pass. If you changebin/mcp_tool_catalog.py, regenerate the catalog/inventory and update the "N tools" counts in the same change. Full rationale: the "Pre-push process — ALL agents" section indocs/AGENT_INSTRUCTIONS.md. This is enforced by the local hook AND CI, not just convention. The leakage scan runs inpython3and compiles each prohibited pattern independently — do NOT fold it back into onegrep -E, where a single pattern the platform's grep rejects disables the whole policy while still printing "no leakage detected". To confirm the gate is alive on this box:python bin/prepush/scan_diff.py --selftest --patterns <policy>(exits non-zero if the policy will not compile). -
Edited anything under
bin/? Runpython bin/gen_tool_inventory.py. Eachbin/script has a generated page underdocs/tools/stamped with a hash of its source, andtests/test_generated_docs_fresh.py::test_tool_pages_are_freshfails when the source moves without the page. This is a THIRD generator, separate fromgen_tool_manifest.pyandgen_mcp_inventory.py(which cover the MCP catalog), and neither the pre-push hook norcheck_tool_catalog_drift.pyruns it — only the full suite catches it, at the end of a ~5.5-minute run. Cheapest habit: regenerate right after the edit, not after the failure. (Hit three times in one session, 2026-09-08.) -
Cutting a release (version bump): The version has ONE source of truth —
pyproject.toml[project].version. Do NOT hand-edit version strings in the derived manifests. Instead: (1) bumppyproject.toml, (2) runpython bin/sync_manifest_versions.py— it writes the new version into every derived manifest (server.json,mcp-server.json,.claude-plugin/plugin.json,plugins/antigravity/plugin.json,plugins/codex/.codex-plugin/plugin.json,gemini-extension.json; the plugin manifests are served straight frommainto every user's/plugin install), plus the README's PyPI badge (docs/badges/pypi-version.svg) and SECURITY.md's "Supported Versions" row, (3) commit all together.tests/test_tool_count_drift.py::test_all_manifests_synced_to_pyproject_version(runs--check) fails the build if you skip step 2, so a stale manifest can't ship. Plugin manifest descriptions say "100+ MCP tools", never an exact count (also test-guarded).
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 Changed · +1 lines · +48 tokens per session 93fe0ede38f4
- 2d ago Changed · +4 lines · +78 tokens per session 1aece1104965
- 16d ago Changed · +4 lines · +173 tokens per session 420a41714738
- 18d ago Changed · +5 lines · +107 tokens per session scan B → D 9594399c3533
- 1mo ago Changed · +2 lines · +195 tokens per session cc1d4863d017
- 1mo ago First seen · 62 lines · 1,300 tokens per session scan B 27cc57e4d8a5
m3-memory CLAUDE.md is an instructions file published in the GitHub repository skynetcmd/m3-memory (29 stars, last pushed yesterday), licensed Apache-2.0. It adds 1,901 tokens to every session, about $0.0076 per session on Opus 5.5. A static security scan graded it D with 2 findings (hidden instructions, reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.