aragora CLAUDE.md

Project-specific instructions for using Claude Code safely in the Aragora codebase, including isolated work areas and coordination rules.

In plain words
What is it for?
Use them when working on Aragora with Claude Code, especially before coordinating with other agents, changing protected files, or opening pull requests.
Why use it?
They help prevent separate coding sessions from overwriting one another and identify rules for protecting the main code and release process.

Instructions file

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/claude-md
Clone the repo
git clone --depth 1 https://github.com/synaptent/aragora
Per session 7,950 This file is loaded in full into every session.
When invoked 7,950 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 $0.07950 $0.07950
Opus 5 $0.03975 $0.03975
Sonnet 5 $0.01590 $0.01590
Haiku 4.5 $0.00795 $0.00795

Measured 3d ago against content hash 124a6de221d9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

aragora CLAUDE.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 3d 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.

**NEVER** use raw `find .worktrees -exec rm -rf` or similar ad-hoc deletion.
CLAUDE.md · 565 lines

How it starts

The opening of the file, as written. The whole thing — 565 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Claude Code Integration Guide

Context for Claude Code when working with the Aragora codebase.

Multi-Agent Coordination: If multiple AI agents are working on this codebase, check docs/COORDINATION.md before starting. See docs/AGENT_ASSIGNMENTS.md for recommended focus areas by track.

Operating Contract: Every autonomous agent (Claude Code, Codex CLI, Droid, agent-bridge harnesses) operates under docs/AGENT_OPERATING_CONTRACT.md: always-allowed actions, approval-required actions, the "break unreleased branch behavior freely; never break main / public API / release flow / CI" rule, and main-red incident mode. Read it before opening PRs that touch workflows, runner labels, public surfaces, or protected files.

Worktree Isolation (CRITICAL)

Every Claude Code session MUST run in an isolated worktree. Multiple sessions share this repo — editing files in the main directory causes concurrent overwrites.

Automatic isolation (3 layers)

  1. Preferred: claude-wt wrapper — Launch Claude via ./scripts/claude-wt instead of claude. Creates a fresh worktree automatically. Pass --resume to reuse an existing one.
  2. Fallback: SessionStart hook — If launched without the wrapper, a hook detects you're in the main directory and outputs a warning. When you see this warning, call EnterWorktree before making any file edits.
  3. Background cleanup — A LaunchAgent runs every 5 minutes, reconciling worktrees with main (merge strategy) and cleaning up stale ones after 24h. Branches are auto-deleted after merge.

Worktree cleanup (IMPORTANT)

NEVER use raw find .worktrees -exec rm -rf or similar ad-hoc deletion. This destroys active worktrees with uncommitted work. Always use the safe helpers:

# Safe cleanup (preferred) — respects TTL, checks merge status
python3 scripts/codex_worktree_autopilot.py cleanup --base main --ttl-hours 24

# Per-worktree safe removal — checks for blockers first
python3 scripts/safe_worktree_cleanup.py inspect <worktree-path>
python3 scripts/safe_worktree_cleanup.py remove <worktree-path>

# Minimal safe option — only prunes already-deleted directories
git worktree prune --expire=now

Read the full file on GitHub · 565 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. 3d ago First seen · 565 lines · 7,950 tokens per session scan C 124a6de221d9

Subscribe to this mod's changes

aragora CLAUDE.md is an instructions file published in the GitHub repository synaptent/aragora (11 stars, last pushed 3d ago), licensed MIT. It adds 7,950 tokens to every session, about $0.0398 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

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

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

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

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 · 4,345 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

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