aragora AGENTS.md

Repository instructions for Aragora, a system where multiple AI agents review information and debate decisions. They describe the agents involved and rules for safely operating concurrent coding sessions with Git worktrees.

In plain words
What is it for?
Use them when running autonomous agents in Aragora, managing high-change sessions, using disposable worktrees, or following the project’s operating rules.
Why use it?
They reduce conflicts and accidental damage when many coding agents work on the same project or make decisions together.

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/synaptent/aragora/agents-md
Clone the repo
git clone --depth 1 https://github.com/synaptent/aragora

Made for: Codex, OpenCode.

Per session 4,728 This file is loaded in full into every session.
When invoked 4,728 The same file — it is already loaded in full.
Security scan C 1 finding. 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 $0.04728 $0.04728
Opus 5 $0.02364 $0.02364
Sonnet 5 $0.00946 $0.00946
Haiku 4.5 $0.00473 $0.00473

Measured 2d ago against content hash 4ef9882d1b02, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

aragora AGENTS.md scanned grade C with 1 finding 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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

- Do not delete side worktrees with raw `git worktree remove` plus `rm -rf`.
AGENTS.md · 381 lines

How it starts

The opening of the file, as written. The whole thing — 381 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Aragora Agents

Aragora is the control plane for multi-agent vetted decisionmaking across organizational knowledge and channels. It implements structured vetted decisionmaking through a society of heterogeneous AI agents. This document describes the agent system architecture.

Operating Contract: Autonomous CLI agents (Claude Code, Codex CLI, Factory Droid, Aider, the agent-bridge harnesses) working in this repository operate under docs/AGENT_OPERATING_CONTRACT.md — the always-allowed / approval-required matrix, the "break unreleased branch behavior freely; never break main / public API / release flow / CI" rule, and main-red incident mode. That contract governs how agents execute against the repo. This document describes what agents are registered as runtime debate participants (the 46-agent registry).

Worktree Autopilot (High-Churn Sessions)

When many agents are committing concurrently, use disposable worktrees with frequent reconciliation.

  • Start sessions with ./scripts/codex_session.sh (or make codex-session). This writes an active-session lock so background maintenance skips in-use worktrees.
  • Do not delete side worktrees with raw git worktree remove plus rm -rf. Inspect/remove them with python3 scripts/safe_worktree_cleanup.py so active-session locks and open PR branches block accidental deletion.
  • Auto-heal unexpected worktree/branch drift with: python3 scripts/codex_worktree_autopilot.py ensure --agent codex --base main --reconcile --print-path
  • Prefer one-shot upkeep during rapid churn: python3 scripts/codex_worktree_autopilot.py maintain --base main --strategy merge --ttl-hours 24
  • Reconcile managed sessions with: python3 scripts/codex_worktree_autopilot.py reconcile --all --base main
  • Remove stale managed worktrees with: python3 scripts/codex_worktree_autopilot.py cleanup --base main --ttl-hours 24
  • Optional macOS daemon: make worktree-maintainer-install for periodic background reconcile-only upkeep.

Read the full file on GitHub · 381 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. 2d ago First seen · 381 lines · 4,728 tokens per session scan C 4ef9882d1b02

Subscribe to this mod's changes

aragora AGENTS.md is an instructions file published in the GitHub repository synaptent/aragora (11 stars, last pushed 2d ago), licensed MIT. It adds 4,728 tokens to every session, about $0.0236 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

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

buildNext

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

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

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

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 · 7,040 tokens

langchain 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 · 4,345 tokens