AgentsAtlas AGENTS.md

A set of project instructions for AgentsAtlas, a workflow that organizes coding work into planned phases and tracked milestones.

In plain words
What is it for?
Use it to initialize a project workflow, create and execute phase plans, check status, review changes, handle outside issues, and restore context after clearing a session.
Why use it?
It keeps progress, plans, outcomes, and command documentation in known places, so an agent can resume work and follow the same process.

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/avinashp/agentsatlas/agents-md
Clone the repo
git clone --depth 1 https://github.com/AvinashP/AgentsAtlas

Made for: Codex, OpenCode.

Per session 297 This file is loaded in full into every session.
When invoked 297 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 $0.00297 $0.00297
Opus 5 $0.00148 $0.00148
Sonnet 5 $0.00059 $0.00059
Haiku 4.5 $0.00030 $0.00030

Measured 2d ago against content hash d69852291977, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

AgentsAtlas 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.

AGENTS.md · 38 lines

What it actually says

Atlas Workflow

Use Atlas skills as thin routers to canonical Claude command docs.

Planning State

  • .planning/STATE.md tracks current status, active phase, and current plan file.
  • .planning/ROADMAP.md defines milestones/phases and target outcomes.
  • .planning/phases/{NN}-PLAN.md stores the active executable phase plan.
  • .planning/phases/{NN}-SUMMARY.md stores execution outcomes and deviations.

Skills to Use

  • atlas-init: Initialize project workflow artifacts.
  • atlas-plan: Create executable phase plan.
  • atlas-execute: Execute current plan tasks.
  • atlas-status: Check project progress.
  • atlas-sync: Restore context after /clear.
  • atlas-triage: Pull and triage external issues.
  • atlas-complete: Complete current milestone.
  • atlas-review: Review code changes.

Canonical Command Docs

  • commands/atlas/init.md
  • commands/atlas/plan.md
  • commands/atlas/execute.md
  • commands/atlas/status.md
  • commands/atlas/sync.md
  • commands/atlas/triage.md
  • commands/atlas/complete.md
  • commands/atlas/review.md

Sync Workflow Artifacts

  • Source of truth: commands/atlas/manifest.json
  • Re-generate wrappers/docs/plugin command list: node scripts/sync-atlas-artifacts.mjs
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. 2d ago First seen · 38 lines · 297 tokens per session scan A d69852291977

Subscribe to this mod's changes

AgentsAtlas AGENTS.md is an instructions file published in the GitHub repository AvinashP/AgentsAtlas (7 stars, last pushed 3mo ago), licensed MIT. It adds 297 tokens to every session, about $0.0015 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.