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/AGENTS.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/agents-md)<a href="https://agentmods.dev/instructions/angelnicolasc/graymatter/agents-md"><img src="https://agentmods.dev/badge/instructions/angelnicolasc/graymatter/agents-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/angelnicolasc/graymatter/agents-md"><img src="https://agentmods.dev/badge/instructions/angelnicolasc/graymatter/agents-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 | $0.01779 | $0.01779 |
| Opus 5.5 | $0.00712 | $0.00712 |
| Sonnet 5.5 | $0.00356 | $0.00356 |
| Haiku 4.5 | $0.00178 | $0.00178 |
Grade A, and why
graymatter AGENTS.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 18d 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 — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
If you're an AI agent (Claude Code, OpenCode, Codex, Cursor, Antigravity, custom MCP client) operating in this repo, read this first. Full operational manual:
docs/AGENTS.md.
This repo is a memory system for AI agents. While you work here, you also get to use it: it's wired into your MCP toolbelt as seven tools that persist facts and checkpoints across sessions.
Your tools
| Tool | Required params | Optional |
|---|---|---|
memory_search |
agent_id, query |
top_k (default 8), explain (boolean, default false), min_confidence, confidence_weight |
memory_search_batch |
agent_id, queries |
top_k (default 8), min_confidence, confidence_weight |
memory_add |
agent_id, text |
confidence |
memory_alias |
agent_id, term, equivalents |
— |
memory_reflect |
action (add|update|forget|link|pin|unpin), plus at least one explicit valid agent_id (canonical) or agent (deprecated alias; agent_id wins when both are valid) |
text, target (which one is required depends on action — for forget/pin/unpin, either works) |
checkpoint_save |
agent_id |
state (JSON-encoded string) |
checkpoint_resume |
agent_id |
on_missing (enum error|empty, default error) |
memory_reflectusesagent_id(canonical since ADR-014). The other six also useagent_id. The deprecated aliasagentis still accepted for compatibility;agent_idwins when both are valid. Identity is explicit and required at runtime for both stdio and HTTP. Each supplied identity must be a non-empty string that is not entirely whitespace; an invalid field is rejected even when the other is valid. See the reflect contract.
memory_reflect also accepts confidence for add and update only.
Confidence options
These options are available since v0.20.0 and are absent from v0.19.1.
verified, inferred and unverified are the writer's declarations, not
verification performed by GrayMatter. An omitted label on add remains legacy
inferred; an omitted label on update is the minimum of inferred and the
effective confidence of every live target. A revision does not inherit a pin.
Generated summaries follow that same conservative rule; facts produced by
LLM extraction are unverified. Pin, decay and access tracking preserve labels.
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.
- 18d ago Changed 0e1ce263244f
- 22d ago Changed · +62 tokens per session 2ea394f66003
- 25d ago Changed · +25 lines · +377 tokens per session 0d6487df855d
- 1mo ago Changed · +16 tokens per session cc73eb7c87cc
- 1mo ago Changed · +2 lines · +103 tokens per session 2cce1939d8c1
- 1mo ago Changed · +17 lines · +220 tokens per session c4180dc49c48
- 1mo ago First seen · 73 lines · 1,001 tokens per session scan A c90d6f6b638a
graymatter AGENTS.md is an instructions file published in the GitHub repository angelnicolasc/graymatter (488 stars, last pushed 18d ago), licensed MIT. It adds 1,779 tokens to every session, about $0.0071 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 2026-08-30.
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).
vscode model-prompts.instructions.md
Model-specific prompt authoring and registry guidelines.