codemap AGENTS.md

Repository instructions for Codemap, a tool that indexes JavaScript, TypeScript, and CSS structure in a local SQLite database so an agent can query code relationships.

In plain words
What is it for?
Use them when working on Codemap, its agent rules, documentation, architecture, hooks, or code-analysis features.
Why use it?
They direct the agent to the project’s rules for reading documentation, changing code, verifying work, and avoiding skipped safeguards.

Instructions file for CodexOpenCode

Install

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.

agentmods
npx agentmods add instructions/stainless-code/codemap/agents-md
Clone the repo
git clone --depth 1 https://github.com/stainless-code/codemap

Made for: Codex, OpenCode.

Per session 632 This file is loaded in full into every session.
When invoked 632 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00632 $0.00632
Opus 5 $0.00316 $0.00316
Sonnet 5 $0.00126 $0.00126
Haiku 4.5 $0.00063 $0.00063

Measured yesterday against content hash 3ba6d2b54cd7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

codemap 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.

AGENTS.md · 25 lines

What it actually says

Agent instructions

Full .agents/ hub: .agents/README.md.

Canonical read order: .agents/rules/agents-first-convention.md · .agents/rules/agents-tier-system.md (START HERE).

Topic Link
File conventions .agents/rules/agents-first-convention.md
Tier system .agents/rules/agents-tier-system.md
Tracer bullets .agents/rules/tracer-bullets.md
Pre-commit hooks .agents/rules/no-bypass-hooks.md
Verify each step .agents/rules/verify-after-each-step.md
Authoring discipline .agents/rules/authoring-discipline.md
Unslop .agents/skills/unslop/SKILL.md
Architecture priming .agents/rules/architecture-priming.md
Consumer surfaces .agents/rules/consumer-surfaces.md
Docs governance .agents/rules/docs-governance.md
PR comments .agents/rules/pr-comment-fact-check.md
Plan-PR inspiration .agents/rules/plan-pr-inspiration-discipline.md

Intent (not always-on): agents-tier-system, ask-agents, audit-pr-architecture, authoring-discipline, codemap, diagnosing-bugs, docs-governance, docs-lifecycle-sweep, docs-voice, domain-modeling, grill-me, grilling, grill-with-docs, harden-pr, improve-codebase-architecture, pr-comment-fact-check, product-tenets, tdd, teach, tracer-bullets, update-docs, verify-after-each-step, writing-agents-config, writing-great-skills.

Human Day-1: README Getting Started · .github/CONTRIBUTING.md.

Changes

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.

  1. yesterday First seen · 25 lines · 632 tokens per session scan A 3ba6d2b54cd7

Subscribe to this mod's changes

codemap AGENTS.md is an instructions file published in the GitHub repository stainless-code/codemap (8 stars, last pushed 7d ago), licensed MIT. It adds 632 tokens to every session, about $0.0032 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.