codesteer-atlas: Instructions file for Codex

AGENTS.md

codesteer-atlas AGENTS.md is an instructions file for Codex, OpenCode from LuisCarlosLopes/codesteer-atlas. It costs 680 tokens per session, scanned A, original, MIT.

A set of project instructions for coding agents working on the CodeSteer Atlas repository. It explains which code-search tools to use, which project rules take priority, and how the Python project is managed.

In plain words
What is it for?
Orienting within the project, finding implementations with Atlas search, checking project relationships, rebuilding the search index, and following its testing and setup practices.
Why use it?
It gives an agent a shared way to explore an unfamiliar codebase and follow the repository’s rules. This reduces blind file searching and conflicts between different instruction files.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions CLAUDE.md.

This is LuisCarlosLopes/codesteer-atlas's own configuration. It tells Codex and OpenCode how to work on codesteer-atlas itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything codesteer-atlas configures →

Reuse

Borrowing it

Nothing to install: this file belongs to LuisCarlosLopes/codesteer-atlas. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/LuisCarlosLopes/codesteer-atlas/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/LuisCarlosLopes/codesteer-atlas

Made for: Codex, OpenCode.

Wrote 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.

agentmods badge for codesteer-atlas AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/luiscarloslopes/codesteer-atlas/agents-md.svg)](https://agentmods.dev/instructions/luiscarloslopes/codesteer-atlas/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/luiscarloslopes/codesteer-atlas/agents-md"><img src="https://agentmods.dev/badge/instructions/luiscarloslopes/codesteer-atlas/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 680 This file is loaded in full into every session.
When invoked 680 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00680 $0.00680
Opus 5 $0.00340 $0.00340
Sonnet 5 $0.00136 $0.00136
Haiku 4.5 $0.00068 $0.00068

Measured 7d ago against content hash 2ac45f5511c8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

codesteer-atlas 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 7d 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.

AGENTS.md · 37 lines

How it starts

The opening of the file, as written. The whole thing — 37 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Leia CLAUDE.md para detalhes de arquitetura.

Busca de código (MCP codesteer-atlas)

Use as tools do MCP antes de grep/rg/find/glob ou leitura em massa.

Objetivo Tool
Se orientar num projeto desconhecido (chame primeiro) atlas_brief
Onde algo está implementado atlas_search
Conectividade, hubs e rationale atlas_graph
Diagnóstico do índice atlas_status
(Re)indexar atlas_index

atlas_search (2 passos): retorna só metadados por padrão — localize com path_prefix/language/top_k baixo; depois Read nas linhas ou include_content=true nos poucos hits relevantes. Não chame atlas_status antes.

Precedência de governança (CodeSteer)

.memory-bank/operational-memory.md é memória operacional do repositório: problemas locais, gotchas e como mitigar — não substitui a camada normativa da Constitution.

Em todas as tarefas, as regras em .memory-bank/constitution.md prevalecem.

Cursor Cloud specific instructions

Pure-Python package managed by uv (Python 3.11–3.13). Standard commands live in CLAUDE.md; the startup update script already runs uv sync --group dev, so deps are ready.

  • Two runtime entry points (both via uv run): atlas-index (CLI indexer, writes .code-index/) and atlas-serve (long-running MCP stdio server). There is no web UI, database server, or network service — everything is local/offline.
  • atlas-serve speaks JSON-RPC over stdio and does not exit; launch it from an MCP client (e.g. fastmcp Client + StdioTransport) or a tmux/background session, never expecting it to return.
  • The server needs a built index first. atlas_search raises an actionable error if .code-index/ is missing — run uv run atlas-index --workspace . before serving/searching. .code-index/ is gitignored and not persisted by the repo.
  • First atlas-index run downloads the fastembed ONNX model (all-MiniLM-L6-v2) and needs one-time network access; subsequent runs are fully offline.
  • Point a running server at an existing index with ATLAS_INDEX_DIR=/workspace/.code-index (or --index-dir); otherwise it falls back to .code-index relative to CWD (see resolve_index_dir() in server.py).
  • Lint: uv run --with ruff ruff check pulls an unpinned ruff. Newer ruff (0.16.x) flags many pre-existing style findings that the pinned CI ruff (see .github/workflows/ci.yml) does not; treat lint drift as pre-existing, not something you introduced.

Read the full file on GitHub · 37 lines

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. 7d ago First seen · 37 lines · 680 tokens per session scan A 2ac45f5511c8

Subscribe to this mod's changes

codesteer-atlas AGENTS.md is an instructions file published in the GitHub repository LuisCarlosLopes/codesteer-atlas (0 stars, last pushed 2d ago), licensed MIT. It adds 680 tokens to every session, about $0.0034 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.

Related

Other instructions, from other repositories

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.

openai/codex · 5,153 tokens

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).

microsoft/vscode · 6,785 tokens

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.

vercel/next.js · 7,296 tokens

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.

langchain-ai/langchain · 4,469 tokens

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).

microsoft/vscode · 5,001 tokens

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.

github/spec-kit · 7,104 tokens