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/cranot/roam-code/agents-mdgit clone --depth 1 https://github.com/Cranot/roam-codeWhat 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 | $0.14242 | $0.14242 |
| Opus 5 | $0.07121 | $0.07121 |
| Sonnet 5 | $0.02848 | $0.02848 |
| Haiku 4.5 | $0.01424 | $0.01424 |
Grade A, and why
roam-code 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 — 834 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — roam-code development guide
What this project is
roam-code is a local codebase intelligence CLI for developers and AI coding agents.
It pre-indexes symbols, call graphs, dependencies, architecture, and git history into
a local SQLite DB. 287 commands · 246 MCP tools (17 in the default core preset) · 28 languages · local analysis · zero API keys.
Authoritative counts (AST-derived, env-independent): command_count: 287 · canonical_count: 280 · category_count: 7 · mcp tools registered: 246 · mcp tools in core preset: 17. The roam surface --json envelope additionally exposes mcp_tool_count_by_preset for per-preset counts.
Package: roam-code on PyPI. Entry point: roam.cli:cli.
Documentation Hub
- Dogfood corpus (read for quality lessons):
internal/dogfood/— 212-eval corpus + 6 systemic-pattern synthesis. Single most important reference for understanding what good roam-command behavior looks like. Start withinternal/dogfood/README.md. (Private — gitignored; not shipped to PyPI/GitHub.) - Getting started tutorial:
templates/distribution/landing-page/docs/getting-started.html - Command reference with examples:
templates/distribution/landing-page/docs/command-reference.html - Architecture guide and diagram:
templates/distribution/landing-page/docs/architecture.html - Live URL: https://roam-code.com/docs/
Where files go (private vs public)
This repo is public. The placement rule is physical, not pattern-based:
internal/— the ONE private folder. Wholesale gitignored. Everything that shouldn't be on GitHub goes here: session memos, sprint plans, release-readiness drafts, monetization research, dogfood batches, smoke results, generated test fixtures, scratch notes, anything you'd be uncomfortable seeing in a public diff. Sub-conventions:internal/dogfood/(eval corpus),internal/planning/(session / sprint / release memos).- Everything else — public by default.
src/,tests/,templates/,dev/, root files. No magic in the gitignore, no whitelists, no per-extension rules.
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 · 834 lines · 14,242 tokens per session scan A 383e4153dc7c
roam-code AGENTS.md is an instructions file published in the GitHub repository Cranot/roam-code (510 stars, last pushed 6d ago), licensed Apache-2.0. It adds 14,242 tokens to every session, about $0.0712 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
codemap AGENTS.md
Instructions for stainless-code/codemap, a project described as: Cut AI-agent token waste 90% — query a local SQLite structural index of your JS/TS/CSS codebase with SQL in one round-trip instead of 3–5 file reads. Symbols, imports, calls, components, CSS tokens, coverage, markers. CLI, MCP (21 tools), HTTP, GitHub…
nexus-mcp CLAUDE.md
Claude Code instructions for jaggernaut007/nexus-mcp, covering nexus-mcp, use nexus-mcp tools before built-in tools, known limitations, structure (all implemented) and commands.
nexus-mcp AGENTS.md
AGENTS.md instructions for jaggernaut007/nexus-mcp, covering nexus-mcp agent guidelines, architecture, stack, key constraints and testing.
nexus-mcp GEMINI.md
Gemini CLI instructions for jaggernaut007/nexus-mcp: Read AGENTS.md at the repo root — it is the single source of truth for this project (stack, commands, Definition of Done, code standards). Also read PROGRESS.md for current session state before starting work.
mcp-server AGENTS.md
AGENTS.md instructions for The-Code-Registry/mcp-server, covering agents.md, mcp endpoints, discovery, client compatibility note (cursor / callmcptool wrappers) and authentication.
remembrallmcp CLAUDE.md
Claude Code instructions for roboticforce/remembrallmcp, covering remembrallmcp, quick reference, build & run, start database and build everything.