matilha-skills: Instructions file for Claude Code

AGENTS.md

matilha-skills AGENTS.md is an instructions file for Claude Code, Codex, OpenCode from danilods/matilha-skills. It costs 758 tokens per session, scanned B, original, MIT.

Repository instructions for Matilha, a planning and process framework for complex projects using AI agents. It organizes work into phases and assigns phase-specific skills while keeping the human responsible for decisions and approval points.

In plain words
What is it for?
Use them to determine project state, choose the next phase, coordinate agents, organize work in parallel worktrees, and review results at defined gates.
Why use it?
They provide a repeatable structure for long projects so agents work on the right tasks at the right stage and important decisions remain with the person leading the project.

Instructions file for Claude CodeCodexOpenCode

Written for Claude Code and Codex and OpenCode: Claude Code plugin machinery, but also reads ~/.codex or $CODEX_HOME. Also seen: mentions subagents; names the TodoWrite tool; mentions Claude Code.

This is danilods/matilha-skills's own configuration. It tells Claude Code, Codex and OpenCode how to work on matilha-skills 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 matilha-skills configures →

Reuse

Borrowing it

Nothing to install: this file belongs to danilods/matilha-skills. 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/danilods/matilha-skills/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/danilods/matilha-skills

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 matilha-skills AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/danilods/matilha-skills/agents-md.svg)](https://agentmods.dev/instructions/danilods/matilha-skills/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/danilods/matilha-skills/agents-md"><img src="https://agentmods.dev/badge/instructions/danilods/matilha-skills/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 758 This file is loaded in full into every session.
When invoked 758 The same file — it is already loaded in full.
Security scan B 1 finding. 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 $0.00758 $0.00758
Opus 5 $0.00379 $0.00379
Sonnet 5 $0.00152 $0.00152
Haiku 4.5 $0.00076 $0.00076

Measured 7d ago against content hash 90b2837f72e5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade B, and why

matilha-skills AGENTS.md scanned grade B 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 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

You are reading this because Matilha is available. On Codex CLI, skills load natively — when a skill's description matches user intent, follow its instructions. Some skills dispatch subagents; Codex requires `multi_agent
AGENTS.md · 53 lines

How it starts

The opening of the file, as written. The whole thing — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Matilha — Cognitive + Methodological Harness

You lead. Agents hunt. A harness for building complex projects with AI.

Matilha preserves discipline across multi-week projects by activating phase-appropriate skills automatically. The human stays in the decision seat (intent, gates, judgment); the agents execute (parallel worktrees, per-SP focus, gated output).

How this loads in Codex (and for contributors)

You are reading this because Matilha is available. On Codex CLI, skills load natively — when a skill's description matches user intent, follow its instructions. Some skills dispatch subagents; Codex requires multi_agent = true in ~/.codex/config.toml for subagent features. See docs/platform-tool-mapping.md for exact Codex tool equivalents (spawn_agent / wait / close_agent, etc.).

For contributors authoring new skills: read docs/matilha/skill-authoring-guide.md before writing. Strict frontmatter is load-bearing — sloppy descriptions produce invisible skills.

Phases (0-70)

Matilha organizes work across 8 phases. Each has a skill entry point.

Phase Purpose Entry skill
0 Project state + next action matilha-howl
10 Discovery / research matilha-scout
20-30 Spec + plan authoring matilha-plan
40 Dispatch + merge (waves, SPs) matilha-hunt, matilha-gather
50 Quality review matilha-review (Wave 3c planned)
60 Knowledge capture matilha-den
70 Reusable artifacts matilha-pack
init Bootstrap new project matilha-init
design UX/UI guidance (cross-phase) matilha-design

See docs/matilha/naming-conventions.md for skill prefix rules and docs/matilha/companions-contract.md for how companion packs (UX, growth, design, security, harness) plug in.

Read the full file on GitHub · 53 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. 7d ago First seen · 53 lines · 758 tokens per session scan B 90b2837f72e5

Subscribe to this mod's changes

matilha-skills AGENTS.md is an instructions file published in the GitHub repository danilods/matilha-skills (2 stars, last pushed 4mo ago), licensed MIT. It adds 758 tokens to every session, about $0.0038 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). 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