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/blazity/atlas/agents-mdgit clone --depth 1 https://github.com/Blazity/atlasWhat 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 | $0.00401 | $0.00401 |
| Opus 5 | $0.00200 | $0.00200 |
| Sonnet 5 | $0.00080 | $0.00080 |
| Haiku 4.5 | $0.00040 | $0.00040 |
Grade A, and why
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 2d 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.
What it actually says
Atlas Core — Project AI Instructions
Atlas Core is the installable layer of Blazity's Atlas standard for AI-assisted engineering: the atlas init / atlas doctor CLI, the managed setup and review skills, and deterministic workspace scaffolding that keeps a repository's AI context (memory, vocabulary, plans, decisions, review artifacts) healthy and machine-checkable.
Operating Rules
- Inside this repo ALWAYS run the local CLI:
npm run atlasornode bin/atlas.js. Never run the publishednpx @blazity-atlas/corepackage against this worktree — the publisheddoctor --fixwould overwrite unreleased managed skill edits with the released versions (channel drift). - Run the full
npm testbefore any commit. - Conventional commits matching the existing
git log --oneline -15style:type(scope): message, first line only. - English everywhere — code, comments, commits, docs.
- Vocabulary lives in
.ai/LANGUAGE.md; decisions live in.ai/decisions/adrs/.
Atlas Artifact Paths
.ai/config.json is the source of truth for AI artifact locations in this repository.
Before writing plans, research, decisions, ADRs, results, memory, vocabulary, or skill outputs, resolve the destination through artifactRoot, paths, and pathAliases.
If an imported skill, template, or instruction mentions a different path, map it through .ai/config.json before reading or writing files.
Do not create new documentation roots unless .ai/config.json explicitly allows them.
Atlas Documentation Rules
Durable documentation records needs, decisions, and reasons — never individuals or internal process. Write "memory was needed to persist context across runs", not " wanted memory". Keep personal names, private schedules, internal-only references, and absolute local paths out of workspace artifacts.
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.
- 2d ago First seen · 27 lines · 401 tokens per session scan A 163293a7e028
atlas AGENTS.md is an instructions file published in the GitHub repository Blazity/atlas (24 stars, last pushed 1mo ago), licensed MIT. It adds 401 tokens to every session, about $0.0020 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
fastagent AGENTS.md
Instructions for fastagent-sh/fastagent, covering fastagent — agent guide, what this is, source of truth, repo map and devx principle stack.
codex-project-skill-manager AGENTS.md
Instructions for WildPigKing/codex-project-skill-manager, covering codex project & skill manager, product boundary, startup routing, consent contract and repository records.
trellis AGENTS.md
Instructions for craigcossairt/trellis, covering agents.md , project, what i need from agents, current state - source of truth pointers and tech stack.
scopeglass AGENTS.md
Instructions for zackabrah/scopeglass, covering scopeglass contributor instructions, project, commands, conventions and boundaries.
agentic-coding-workflow AGENTS.md
Instructions for abhilash-m96/agentic-coding-workflow, covering agentic coding workflow, rules, step 1 — understand the full scope, step 2 — propose the chunk plan and step 3 — write the finalised plan.
android-qa-kit AGENTS.md
Instructions for willbytee-sudo/android-qa-kit, covering agents.md — setting up and driving an android device, 1. how to work with the user, 2. start by finding out what's already there, 3. what you can do in each mode and 4. if there's no device: ask first.