agent-triforce: Instructions file for Claude Code

CLAUDE.md

agent-triforce CLAUDE.md is an instructions file for Claude Code from ArtemioPadilla/agent-triforce. It costs 3,795 tokens per session, scanned A, original, MIT.

Instructions for Agent Triforce, a development system that assigns product planning, coding, and quality checks to three specialized agents. It also defines commands and checklists for those roles.

In plain words
What is it for?
Use it to plan features, implement them, run security or code-health reviews, and perform release checks with the appropriate agent.
Why use it?
It clarifies who should handle each kind of development work and which checks should happen before changes are accepted.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md.

This is ArtemioPadilla/agent-triforce's own configuration. It tells Claude Code how to work on agent-triforce 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 agent-triforce configures โ†’

Reuse

Borrowing it

Nothing to install: this file belongs to ArtemioPadilla/agent-triforce. 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/ArtemioPadilla/agent-triforce/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/ArtemioPadilla/agent-triforce

Made for: Claude Code.

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 agent-triforce CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/artemiopadilla/agent-triforce/claude-md/github.svg)](https://agentmods.dev/instructions/artemiopadilla/agent-triforce/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/artemiopadilla/agent-triforce/claude-md"><img src="https://agentmods.dev/badge/instructions/artemiopadilla/agent-triforce/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80ร—15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80ร—15 button for agent-triforce CLAUDE.md

Your own site ยท 80ร—15
<a href="https://agentmods.dev/instructions/artemiopadilla/agent-triforce/claude-md"><img src="https://agentmods.dev/badge/instructions/artemiopadilla/agent-triforce/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 3,795 This file is loaded in full into every session.
When invoked 3,795 The same file โ€” it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file โ€” 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 $0.03795 $0.03795
Opus 5 $0.01898 $0.01898
Sonnet 5 $0.00759 $0.00759
Haiku 4.5 $0.00380 $0.00380

Measured 11d ago against content hash 8397f6d7c72a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

agent-triforce CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories โ€” prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency โ€” measured 11d 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.

CLAUDE.md ยท 302 lines

How it starts

The opening of the file, as written. The whole thing โ€” 302 lines โ€” stays where its author put it; the contents beside it link to each section on GitHub.

๐Ÿ”ฑ Agent Triforce โ€” Multi-Agent Development System

System Overview

This project uses 3 specialized agents. Always use the appropriate agent for each task:

  • Prometeo (PM): Product strategy, feature specs, business logic, prioritization
  • Forja (Dev): Architecture, implementation, infrastructure, documentation
  • Centinela (QA): Security audit, code review, testing, compliance, dead code detection

Agent Invocation

Use agents explicitly:

  • "Use Prometeo to define the feature for [X]"
  • "Use Forja to implement [X]"
  • "Use Centinela to audit [X]"

Or use skills:

  • /feature-spec [description] โ†’ Runs with Prometeo
  • /implement-feature [spec-name] โ†’ Runs with Forja
  • /security-audit [scope] โ†’ Runs with Centinela
  • /code-health โ†’ Runs with Centinela
  • /release-check โ†’ Runs with Centinela
  • /review-findings [review-file] โ†’ Runs with Forja
  • /business-review [feature-name] โ†’ Runs with Prometeo

Checklist Methodology

This system applies principles from The Checklist Manifesto (Atul Gawande) and Boeing's checklist engineering (Daniel Boorman). Checklists are not training wheels โ€” they are cognitive safety nets that catch the flaws of memory, attention, and thoroughness inherent in all of us.

Core Philosophy

  • Ineptitude, not ignorance: Failures come from not applying what we already know, not from lack of knowledge
  • Checklists supplement expertise: They are reminders of the most critical steps โ€” not comprehensive how-to guides. They do not replace skill; they enhance it
  • "FLY THE AIRPLANE": Step 1 of any emergency checklist is to remember your primary mission. Never get so lost in process that you forget the goal
  • Discipline is professionalism: The discipline to consult a checklist, no matter how experienced you are, is what separates reliable systems from fragile ones
  • Systems over components: Individually excellent agents aren't enough โ€” they must mesh together through structured coordination

Checklist Design Rules (Boorman's Principles)

Every checklist in this system MUST follow these rules:

  1. Clear pause point: A specific moment where you STOP and consult the checklist
  2. 5-9 killer items only: Focused on the steps most dangerous to skip and most commonly overlooked. Not everything โ€” just the critical few
  3. Under 60 seconds: If it takes longer, it will be skipped or shortcut
  4. Simple, exact wording: No vague language. Each item is a concrete, verifiable action
  5. DO-CONFIRM or READ-DO: Every checklist declares its type (see below)
  6. Field-tested and updated: Checklists evolve based on actual failures and lessons learned. Update them when they catch something new or miss something important

Read the full file on GitHub ยท 302 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. 11d ago First seen ยท 302 lines ยท 3,795 tokens per session scan A 8397f6d7c72a

Subscribe to this mod's changes

agent-triforce CLAUDE.md is an instructions file published in the GitHub repository ArtemioPadilla/agent-triforce (3 stars, last pushed 4mo ago), licensed MIT. It adds 3,795 tokens to every session, about $0.0190 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 2026-08-31.

Related

Other instructions, from other repositories

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 ยท 7,296 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 ยท 5,153 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 ยท 6,785 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart โ€” add a new integration in 5 steps, integration architecture and integrationmanifest โ€” file tracking.

github/spec-kit ยท 7,104 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 ยท 5,001 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 ยท 4,469 tokens