Borrowing it
Nothing to install: this file belongs to abdul-hamid-achik/codemap. 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/abdul-hamid-achik/codemap/main/AGENTS.mdgit clone --depth 1 https://github.com/abdul-hamid-achik/codemapWrote 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/abdul-hamid-achik/codemap/agents-md)<a href="https://agentmods.dev/instructions/abdul-hamid-achik/codemap/agents-md"><img src="https://agentmods.dev/badge/instructions/abdul-hamid-achik/codemap/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/abdul-hamid-achik/codemap/agents-md"><img src="https://agentmods.dev/badge/instructions/abdul-hamid-achik/codemap/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 | $0.03665 | $0.03665 |
| Opus 5.5 | $0.01466 | $0.01466 |
| Sonnet 5.5 | $0.00733 | $0.00733 |
| Haiku 4.5 | $0.00366 | $0.00366 |
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 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 — 228 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Contributor/agent guide for codemap. Product usage lives in docs/ (start at
docs/quick-start.md; agents: docs/agents.md, docs/mcp.md; learning layer:
docs/learn.md; config: docs/configuration.md). Design rationale lives in the
Obsidian vault at ~/notes/projects/codemap/design-rationale.md; live work in the
vault's BACKLOG.md — never in the repo. The in-band agent guide is generated from
internal/app/docs.go (codemap docs [topic]); this file is contributor rules and
invariants, not a second copy of the product contracts — when a contract detail
matters, follow the pointer and read the code/schema.
Project Overview
codemap is local-first code intelligence: a structural code graph (stdlib parsers +
pure-Go tree-sitter for TS/JS/Python; LSP for --precise) plus semantic retrieval
(local veclite, or delegated one-hop to vecgrep) behind one query layer. It answers
questions grep/LSP-alone can't: "who calls this and what tests cover it", "blast
radius of changing this type", "find auth-like code, then show what calls it".
Three surfaces over one store:
- CLI — human commands +
--jsonmachine output (Cobra,cmd/codemap/). - MCP server —
codemap serve(stdio),codemap_*tools (internal/mcp/). - Codemap Studio — Electron app in
desktop/; never reimplements anything, every panel spawnscodemap … --json(seedocs/desktop.md). The terminal Studio TUI was retired.
Highlights: learning layer (atlas/features/flow/processes — summaries are read
from READMEs/package docs/leading comments, never generated), hybrid queries
(context, impact, review, affected), cross-project graph, hash-incremental
reindex with an embedding-profile guard, offline structural queries (one-off precise
relations may launch a language server on demand).
Directory Structure
cmd/codemap/ # Cobra CLI split by domain; every RunE is THIN → session → internal/app.
# Files carry /* Copyright © 2026 abdul hamid <[email protected]> */.
internal/
app/ # shared service layer (CLI + MCP call this; desktop via CLI)
graph/ # SQLite graph store: store/schema/queries/topology/ranking/traversal
extract/ # backends: gosrc, typesrc (go/types), sittersrc (tree-sitter),
# lspsrc, tsscan, rubysrc, luasrc, vuesrc, featuresrc, declarative
lsp/ # hand-rolled LSP client (Content-Length JSON-RPC)
embed/ # embed.Provider + Ollama provider + EmbeddingProfile guard
vector/ # veclite wrapper (one `codemap` collection)
index/ # walk → extract → embed → store; incremental, watcher, import edges
mcp/ # stdio MCP server — thin pass-through to app
daemon/ # fsnotify watcher + control socket
git/ snapshot/ branchstate/ cachestate/ config/ version/
docs/ # VitePress product site ONLY (deployed via Vercel from main)
desktop/ # Codemap Studio (Electron); see "Desktop" under Common Tasks
integrations/ # claude-code plugin, portable agent skill, github-action (generated
# playbook artifacts, pinned by sync tests — not notes)
specs/ # glyphrun E2E specs (*.yml, local only)
schemas/ # versioned JSON schemas for machine contracts (e.g. review v1)
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 Changed · +2 lines · +47 tokens per session 2893315d3a30
- 7d ago Changed · -451 lines · -11,873 tokens per session 5ebb0f5e7da7
- 18d ago Changed · +19 lines · +458 tokens per session c0648dde7a94
- 19d ago Changed · +69 lines · +2,076 tokens per session 8eda85f4189b
- 23d ago Changed · +32 lines · +975 tokens per session f1d31da0ebdc
- 27d ago Changed · +10 lines · +206 tokens per session e2e5b06542e1
- 1mo ago Changed · +6 lines · +125 tokens per session e13d0952a726
- 1mo ago Changed · +95 tokens per session cc18aa983c86
- 1mo ago Changed · +26 lines · +585 tokens per session cf2b71dbe742
- 1mo ago First seen · 515 lines · 10,971 tokens per session scan A aee391d73bdd
codemap AGENTS.md is an instructions file published in the GitHub repository abdul-hamid-achik/codemap (2 stars, last pushed 7d ago), licensed MIT. It adds 3,665 tokens to every session, about $0.0147 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 2026-08-31.
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).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.