Borrowing it
Nothing to install: this file belongs to angelnicolasc/graymatter. 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/angelnicolasc/graymatter/main/CLAUDE.mdgit clone --depth 1 https://github.com/angelnicolasc/graymatterWrote 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/angelnicolasc/graymatter/claude-md)<a href="https://agentmods.dev/instructions/angelnicolasc/graymatter/claude-md"><img src="https://agentmods.dev/badge/instructions/angelnicolasc/graymatter/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 5.1 | $0.00615 | $0.00615 |
| Opus 5 | $0.00308 | $0.00308 |
| Sonnet 5 | $0.00123 | $0.00123 |
| Haiku 4.5 | $0.00061 | $0.00061 |
Grade A, and why
graymatter 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 6d 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.
How it starts
The opening of the file, as written. The whole thing — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
Read this first if someone pointed you at GrayMatter. Three situations, three different answers.
GrayMatter is a single-binary Go memory system for AI agents. Library + CLI +
MCP server + TUI. Facts persist to bbolt with optional vector embeddings, for
roughly a 90% cut in context tokens versus re-injecting full history — the
figure go run ./benchmarks/token_count actually prints at 100 sessions.
A user asked you to set GrayMatter up
Do not read the source for this. Follow Agent setup procedure in the
README: install the binary, graymatter init, graymatter doctor, then tell the user to restart you.
That last step is the one that gets skipped. MCP servers are launched by the
client at startup, so the memory tools will not exist in the session that ran
init, no matter how green doctor looks.
You are working in a project that already uses GrayMatter
AGENTS.md is the operating manual: which tool to call, when, and
with which parameter names. The full version is docs/AGENTS.md.
The one thing that reliably trips agents up: memory_reflect takes agent,
while the other four tools take agent_id. Mixing them up fails validation.
You are contributing to GrayMatter itself
CONTRIBUTING.md covers setup, tests, coverage gates and
code conventions. Two things the tree does not make obvious:
- bbolt is single-writer, and daemon mode is what makes concurrent access
work. One process owns the store and every other one (TUI, MCP server, CLI,
run, the REST server) connects as a client over a Unix domain socket on POSIX, TCP loopback on Windows. On Windows the 256-bit token in the discovery file is the only access control: any local process can reach loopback, and the0600the code passes toos.WriteFileis a POSIX-only guarantee — on Windows the file just inherits its parent directory's ACL. Clients spawn the daemon on first use and it idle-exits when unused.--no-daemonopts out and brings the lock contention back. Seecmd/graymatter/internal/daemon/andpkg/memory/rpc/. - The module is split. The root is the library;
cmd/graymatter/is the CLI and TUI with its owngo.mod, so library consumers do not inherit TUI dependencies.docs/api-stability.mdsays what is stable:graymatter.Memoryis, internal packages are not.
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.
- 6d ago First seen · 48 lines · 615 tokens per session scan A 28563426a996
graymatter CLAUDE.md is an instructions file published in the GitHub repository angelnicolasc/graymatter (465 stars, last pushed yesterday), licensed MIT. It adds 615 tokens to every session, about $0.0031 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
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.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
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).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
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.
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.