coven AGENTS.md

Contributor instructions for Coven, a Rust authority layer with TypeScript integration packages, including worktree, branch, pull-request, and CI practices. A worktree is a separate checkout that lets multiple coding sessions work without changing the same files.

In plain words
What is it for?
Use them before changing Coven, especially when claiming work, creating a branch, preparing a pull request, or running checks.
Why use it?
They help contributors avoid duplicate work and keep the Rust core separate from the TypeScript integration code.

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/opencoven/coven/agents-md
Clone the repo
git clone --depth 1 https://github.com/OpenCoven/coven

Made for: Codex, OpenCode.

Per session 1,698 This file is loaded in full into every session.
When invoked 1,698 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 $0.01698 $0.01698
Opus 5 $0.00849 $0.00849
Sonnet 5 $0.00340 $0.00340
Haiku 4.5 $0.00170 $0.00170

Measured 2d ago against content hash 51468c69173c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

coven 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 · 153 lines

How it starts

The opening of the file, as written. The whole thing — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — coven

Guidance for AI agents (Codex, Claude Code, Hermes, and any Coven familiar) opening pull requests against this repo. Humans: your canonical guide is CONTRIBUTING.md — this is the agent-specific layer on top.

Read first: README.md for what this repo is, and CONTRIBUTING.md for the full contribution bar (including the "Contributor First 10 Minutes" checkout path).


What this repo is (one line)

Coven is a small, boring Rust authority layer with TypeScript integration packages around it. The development loop must keep that boundary clear: core logic stays in Rust; the npm packages are thin integration surface.

Check, enter a worktree, then claim it

Multiple agent sessions (Codex, Claude Code, familiars) frequently run against the same checkout at once, each in its own worktree. Worktrees keep git operations from racing, but they do not stop two sessions from independently building the same issue — which has happened repeatedly, producing duplicate PRs that a session then has to close. Before you touch code:

  1. Check what's already taken. Duplication hides behind divergent branch names — one issue once spawned fix/output-polish, fix/311-output-polish, and fix/output-polish-311 — so branch names alone won't tell you. Check both the shared claim registry and open PRs:

    coven claim status          # active claims, shared across every worktree of this repo
    gh pr list --state open     # is there already a PR for this issue?
    

    If the issue is claimed or already has a PR, pick different work or coordinate.

  2. Create or enter the task worktree. The automatic fallback identity is worktree-scoped, so enter the worktree before acquiring the claim:

    git fetch origin main
    git worktree add -b <branch> /tmp/coven-<branch-slug> origin/main
    cd /tmp/coven-<branch-slug>
    
  3. Claim it with a shared, issue-keyed token — not your working branch name, which no other session can predict:

    coven claim acquire issue-<N>     # e.g. issue-311; a TTL-bounded lock
    

    Claims live in the repo's shared --git-common-dir/agent-claims/, so every worktree and session sees them. For long tasks, extend the TTL with coven claim heartbeat issue-<N>.

Read the full file on GitHub · 153 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 · 153 lines · 1,698 tokens per session scan A 51468c69173c

Subscribe to this mod's changes

coven AGENTS.md is an instructions file published in the GitHub repository OpenCoven/coven (41 stars, last pushed 2d ago), licensed MIT. It adds 1,698 tokens to every session, about $0.0085 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.