grafel AGENTS.md

grafel AGENTS.md is an instructions file for Codex, OpenCode from cajasmota/grafel. It costs 4,728 tokens per session, scanned A, original, MIT.

A contributor instruction file for Grafel, a project with an MCP interface for AI agents. It defines repository rules such as branch use, worktree layout, GitHub account requirements, and documentation locations.

In plain words
What is it for?
Guiding Grafel development, including branch and worktree setup, GitHub operations, architecture decision records, and quality-test fixtures.
Why use it?
It helps coding agents follow the project's contribution process and avoid unsafe or incorrect repository operations.

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

Made for: 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 grafel AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/cajasmota/grafel/agents-md.svg)](https://agentmods.dev/instructions/cajasmota/grafel/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/cajasmota/grafel/agents-md"><img src="https://agentmods.dev/badge/instructions/cajasmota/grafel/agents-md.svg" alt="Measured on agentmods" height="20"></a>
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 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 $0.04728 $0.04728
Opus 5 $0.02364 $0.02364
Sonnet 5 $0.00946 $0.00946
Haiku 4.5 $0.00473 $0.00473

Measured 4d ago against content hash f6b5bdd87117, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

grafel 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 4d 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 · 232 lines

How it starts

The opening of the file, as written. The whole thing — 232 lines — stays where its author put it; the contents beside it link to each section on GitHub.

grafel — Contributor Agent Guide

If you're an AI agent helping develop grafel itself, follow these conventions. End-user-facing guidance for agents calling grafel via MCP is delivered through the MCP instructions handshake (wired into internal/mcp/server.go), not from this file.

Repo conventions

  • Branches: feature branches only, never push to main
  • Worktrees: grafel-worktrees/<branch-name> per concurrent stream
  • GitHub identity: all gh / GitHub operations MUST use the repo owner's personal account (cajasmota) — never any other or secondary (work) account that may be authenticated on the machine. Verify the active account (gh auth status) before any write; if a non-personal account is active, switch back first. (Spawned worker agents are local-only and must not run gh at all — the coordinator owns all GitHub writes.)
  • ADRs in docs/adrs/, numbered sequentially
  • Quality fixtures in internal/quality/golden/; they hold a recall ratchet, not 100% recall. As measured on 72c7848ca (2026-08-08) by scripts/quality/run.sh --runs 1, 6 of 20 fixtures reach 100% must-have recall, 12 fall short, and 2 (groovy-grails-mini, swift-swiftui-mini) carry no expected.json and are not graded at all. Per-fixture figures live in internal/quality/golden/baseline.json; re-derive them with scripts/quality/run.sh --runs 1 --update-baseline. The convention is scripts/quality/run.sh --ratchet: recall may not drop below the recorded baseline, and a rise fails too until you record it. Nothing invokes it for you — .github/workflows/quality.yml is workflow_dispatch only — so run it yourself on any change that touches extraction. The one part that is automatic is go test ./internal/quality -run TestBaseline, which enforces the baseline's structure without indexing anything. (Refs #6231)

Coverage matrix update — mandatory for capability-changing PRs

When your PR adds, modifies, or fixes a capability that's tracked in the coverage matrix, the PR MUST also update docs/coverage/registry.json to reflect the change. The matrix is the source of truth for grafel's capabilities; PRs that ship code without updating the matrix create drift that erodes the matrix's value.

Read the full file on GitHub · 232 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. 4d ago First seen · 232 lines · 4,728 tokens per session scan A f6b5bdd87117

Subscribe to this mod's changes

grafel AGENTS.md is an instructions file published in the GitHub repository cajasmota/grafel (12 stars, last pushed today), licensed MIT. It adds 4,728 tokens to every session, about $0.0236 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.

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