codeatlas-platform: Instructions file for Codex

AGENTS.md

codeatlas-platform AGENTS.md is an instructions file for Codex, OpenCode from giauphan/codeatlas-platform. It costs 444 tokens per session, scanned A, original, MIT.

A repository-specific instruction guide for the CodeAtlas platform. It describes the Express backend, React dashboard, database, coding conventions, tests, and commands used in that project.

In plain words
What is it for?
It helps agents locate backend, dashboard, script, database, and test files and choose the relevant validation commands for a change.
Why use it?
It gives a coding agent the project's layout and rules before it changes code. This helps prevent broad changes, unsafe typing, broken identity boundaries, and missing tests.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md.

This is giauphan/codeatlas-platform's own configuration. It tells Codex and OpenCode how to work on codeatlas-platform 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 codeatlas-platform configures →

Reuse

Borrowing it

Nothing to install: this file belongs to giauphan/codeatlas-platform. 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/giauphan/codeatlas-platform/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/giauphan/codeatlas-platform

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 codeatlas-platform AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/giauphan/codeatlas-platform/agents-md/github.svg)](https://agentmods.dev/instructions/giauphan/codeatlas-platform/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/giauphan/codeatlas-platform/agents-md"><img src="https://agentmods.dev/badge/instructions/giauphan/codeatlas-platform/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.

agentmods 80×15 button for codeatlas-platform AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/giauphan/codeatlas-platform/agents-md"><img src="https://agentmods.dev/badge/instructions/giauphan/codeatlas-platform/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 444 This file is loaded in full into every session.
When invoked 444 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 $0.00444 $0.00444
Opus 5.5 $0.00178 $0.00178
Sonnet 5.5 $0.00089 $0.00089
Haiku 4.5 $0.00044 $0.00044

Measured 15d ago against content hash 0c91a2e6430b, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

codeatlas-platform 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 15d 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 · 58 lines

How it starts

The opening of the file, as written. The whole thing — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CodeAtlas Platform agent guide

Scope and layout

This repository is the CodeAtlas backend platform. The Express/MCP/API code is under src/; tests are under tests/; operational scripts are under scripts/; and the React/Vite dashboard is a separate project in dashboard/. The default local database is data/codeatlas.db.

Working conventions

  • Prefer small, project-scoped changes. Inspect existing patterns and focused tests before editing a behavior.
  • Keep TypeScript strict. Use unknown plus narrowing at untrusted boundaries; do not introduce any to bypass typing.
  • Use ESM imports and comments that explain non-obvious decisions, not syntax.
  • Add or update a focused node:test test whenever behavior changes.
  • Preserve project and tenant identity boundaries. Memory, checkpoint, and reconciliation changes must remain scoped by canonical project_id.

Commands

Run commands from the repository root unless a command says otherwise:

npm run typecheck
npm run build
npm test
npm run test:memory-pipeline

Use the smallest relevant test while iterating. Run the memory-pipeline acceptance check for changes to hooks, capture, checkpoints, dreams, or reconciliation. Dashboard changes require their own checks:

cd dashboard
pnpm test
pnpm run build

Safety

  • Never commit .env, service-account files, API keys, SQLite databases, logs, node_modules, or generated dist output.
  • Treat external requests, transcript payloads, memory records, and MCP input as untrusted. Validate schemas and redact secrets before persistence or logs.
  • Do not remove ignored files or data/ as cleanup; they may contain active local state.
  • Stage only files belonging to the current task. Do not reset, overwrite, or discard unrelated work in a dirty tree.

Git and handoff

Use a focused branch and Conventional Commit message. Before opening a PR, run the relevant checks above and report any checks that require configured local services or credentials instead of fabricating a result.

Read the full file on GitHub · 58 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. 15d ago First seen · 58 lines · 444 tokens per session scan A 0c91a2e6430b

Subscribe to this mod's changes

codeatlas-platform AGENTS.md is an instructions file published in the GitHub repository giauphan/codeatlas-platform (12 stars, last pushed 2d ago), licensed MIT. It adds 444 tokens to every session, about $0.0018 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 2026-10-22.

Related

codeatlas-platform AGENTS.md compared with instructions from other repositories

codeatlas-platform AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
codeatlas-platform AGENTS.mdgiauphan/codeatlas-platformInstructions file122d agoMITA444Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode