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/aminfara/matrix/agents-mdgit clone --depth 1 https://github.com/aminfara/matrixWhat 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 | $0.00854 | $0.00854 |
| Opus 5 | $0.00427 | $0.00427 |
| Sonnet 5 | $0.00171 | $0.00171 |
| Haiku 4.5 | $0.00085 | $0.00085 |
Grade A, and why
matrix 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 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.
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 — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project: MATRIX
Structure
requirements/— Product requirements and backlog (managed by Percy)architecture/— System architecture docs (managed by Archie)database.md— DB schema, tables, indexes, pragmas, design decisionsoverview.md— Module map, tool catalogue, error-handling modelinterface.md— CLI + Web UI architecture, file map, route table, library choices
src/— Source code (server, db, models, requirements, tasks, task-workflow, task-helpers, tools, errors, instructions) plusinterface/sub-folder for CLI + web UIsrc/interface/— CLI (matrix-mcp-cli) and embedded web server for human userscli.js— Entry point binary;commander+@inquirer/prompts; DB path resolutioncommands/— CLI handlers for requirements, tasks, workflow; sharedutils.jsweb/— Express app (server.js) + server-side rendered HTML views (views/)
tests/— Unit tests (vitest, in-memory SQLite)
Development Setup
- Install:
npm install - Start MCP server:
node src/server.js(or via MCP client config) - Start CLI:
node src/interface/cli.js --help(ormatrix-mcp-cliafternpm link) - Start web UI:
node src/interface/cli.js serve [--port 3000]— binds to127.0.0.1only - DB path (CLI):
--matrix-db-patharg >MATRIX_DB_PATHenv var >.matrix/matrix.db - Node.js required: ≥ 22.5.0 (requires
node:sqlitebuilt-in) - Environment variables:
MATRIX_DB_PATH— override default DB path (.matrix/matrix.dbrelative to cwd)
Testing
- Unit tests:
npm test(vitest, all tests use in-memory SQLite viainitDb) - Type check:
npm run typecheck - Current coverage: 112 tests across 6 files — unit tests (requirements, tasks, task-workflow), MCP tool layer integration tests (
tests/tools.test.js), interface service integration tests (tests/interface-services.test.js), and web server HTTP tests (tests/web-server.test.js).
Build & Deploy
- Publish:
npm publish(package name:matrix-mcp, bins:matrix-mcp → src/server.js,matrix-mcp-cli → src/interface/cli.js) - Run via npx:
npx matrix-mcp(run in project cwd so DB resolves correctly)
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 First seen · 54 lines · 854 tokens per session scan A f3cc5ef03c40
matrix AGENTS.md is an instructions file published in the GitHub repository aminfara/matrix (0 stars, last pushed 1mo ago), licensed MIT. It adds 854 tokens to every session, about $0.0043 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 2026-08-31.
Other instructions, from other repositories
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.
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).
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.
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 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).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.