agent-agile: Instructions file for Claude Code

AGENTS.md

agent-agile AGENTS.md is an instructions file for Claude Code, Codex, OpenCode from Peeyushmeher/agent-agile. It costs 485 tokens per session, scanned A, original, MIT.

A repository instruction file for Agent-Agile, a planning and execution system for AI coding agents. It turns ideas into goals, larger work units, and smaller stories, then runs reviews and executes the work in ordered waves.

In plain words
What is it for?
Use its commands to question or import a plan, create goals and epics, divide an epic into stories, execute work in parallel waves, review results, check status, or resume a paused project.
Why use it?
It provides a repeatable path from an uncertain idea to reviewed implementation. Critic panels and review gates help expose weak plans before or during coding.

Instructions file for Claude CodeCodexOpenCode

Written for Claude Code and Codex and OpenCode: ${CLAUDE_PLUGIN_ROOT} variable, but also the file is AGENTS.md. Also seen: reads .claude/ paths; mentions Claude Code; mentions Codex.

This is Peeyushmeher/agent-agile's own configuration. It tells Claude Code, Codex and OpenCode how to work on agent-agile 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 agent-agile configures →

Runs only inside a plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else, and the catalogue could not identify which plugin ships it.

Reuse

Borrowing it

Nothing to install: this file belongs to Peeyushmeher/agent-agile. 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/Peeyushmeher/agent-agile/master/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/Peeyushmeher/agent-agile

Made for: Claude Code, 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 agent-agile AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/peeyushmeher/agent-agile/agents-md.svg)](https://agentmods.dev/instructions/peeyushmeher/agent-agile/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/peeyushmeher/agent-agile/agents-md"><img src="https://agentmods.dev/badge/instructions/peeyushmeher/agent-agile/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 485 This file is loaded in full into every session.
When invoked 485 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 $0.00485 $0.00485
Opus 5 $0.00243 $0.00243
Sonnet 5 $0.00097 $0.00097
Haiku 4.5 $0.00049 $0.00049

Measured 7d ago against content hash 685e35142b68, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

agent-agile 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 · 32 lines

What it actually says

Agent-Agile

Agent-Agile is an agile planning + execution system for AI coding agents: it grills an idea into shape, plans it as OKRs and epics, attacks the plan with an adversarial critic panel, then executes epics in parallel waves with review gates. It runs the same way across harnesses — Claude Code, Codex CLI, OpenCode — because the logic lives in playbooks/, not in per-harness skill files.

Commands

Command Purpose
/aa-grill Idea interrogation → IDEA.md (can reject the idea)
/aa-new-project 8-question intake → OKRs → epics → Epic 1 stories
/aa-import Existing plan: audit → gaps → panel → proceed/reshape/kill
/aa-panel Run the critic panel on the current draft plan
/aa-plan-epic Slice next epic: contracts scope + story cards + waves
/aa-execute-epic Wave 0 → collision check → Wave 1 → Wave 2
/aa-review Present DEMO.md → approve/redo/replan
/aa-autopilot Chain all epics; --gate full-auto|checkpoint
/aa-resume Read STATE.md, pick up the baton
/aa-status Where are we; roadmap + KR progress
/aa-help Command guide + methodology crash course

Playbook root resolution

Resolve the Agent-Agile playbook root: use the first of these that exists — (1) ${CLAUDE_PLUGIN_ROOT}/playbooks, (2) ./.claude/agent-agile/playbooks, (3) ./.agents/agent-agile/playbooks, (4) ~/.claude/agent-agile/playbooks, (5) ~/.agents/agent-agile/playbooks, (6) ./playbooks.

Session state

State lives in .planning/ — open STATE.md first in any session.

No timelines

Agent-Agile never estimates durations, dates, or deadlines, and never asks you for them. Progress is tracked by what's done against the plan, not by how long it took or should take.

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 · 32 lines · 485 tokens per session scan A 685e35142b68

Subscribe to this mod's changes

agent-agile AGENTS.md is an instructions file published in the GitHub repository Peeyushmeher/agent-agile (3 stars, last pushed 1mo ago), licensed MIT. It adds 485 tokens to every session, about $0.0024 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 · 5,182 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