A workflow for carrying out a larger project request through evaluation, planning, delegated implementation, review, and reporting.

Use it for substantial changes that need roles such as product, technical, frontend, backend, content, or quality review.

It provides a repeatable way to coordinate different responsibilities and keep non-trivial work aligned with the project’s directives and acceptance criteria.

How andrew-yangy/gru-ai configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to andrew-yangy/gru-ai. 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/andrew-yangy/gru-ai/main/.claude/skills/directive/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/andrew-yangy/gru-ai

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/andrew-yangy/gru-ai/directive/github.svg)](https://agentmods.dev/skills/andrew-yangy/gru-ai/directive)

Your own site

<a href="https://agentmods.dev/skills/andrew-yangy/gru-ai/directive"><img src="https://agentmods.dev/badge/skills/andrew-yangy/gru-ai/directive/github.svg" alt="Measured on agentmods" height="20"></a>

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

Your own site · 80×15

<a href="https://agentmods.dev/skills/andrew-yangy/gru-ai/directive"><img src="https://agentmods.dev/badge/skills/andrew-yangy/gru-ai/directive.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 170 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,705 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. 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.

Model	Per session	Once invoked
Fable 5.1	$0.00170	$0.02705
Opus 5	$0.00085	$0.01352
Sonnet 5	$0.00034	$0.00541
Haiku 4.5	$0.00017	$0.00270

Measured 10d ago against content hash c664e6329d10, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

directive 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 10d 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/skills/directive/SKILL.md · 135 lines

How it starts

The opening of the file, as written. The whole thing — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Execute Directive

Execute the CEO directive: $ARGUMENTS

Role Resolution — Read First

Before executing, read .claude/agent-registry.json to map roles to agent names. The pipeline uses role-based language throughout. Resolve roles to concrete agent names using the registry:

COO = the agent with "title": "COO" (plans projects, orchestrates execution)
CTO = the agent with "title": "CTO" (architecture, audits, reviews, technical decomposition)
CPO = the agent with "title": "CPO" (product strategy, UX review, user perspective)
CMO = the agent with "title": "CMO" (growth, SEO, content strategy)
Frontend Developer = the agent with "title": "FE" (React, Tailwind, components)
Backend Developer = the agent with "title": "BE" (server, API, infrastructure)
Full-Stack Engineer = the agent with "title": "FS" (cross-domain work)
Data Engineer = the agent with "title": "DE" (pipelines, parsers, indexing)
Content Builder = the agent with "title": "CB" (MDX, documentation, copywriting)
QA Engineer = the agent with "title": "QA" (testing, investigation, validation)
UI/UX Designer = the agent with "title": "UX" (design review, wireframes, visual quality)

Use each agent's id field as the subagent_type value when spawning. Use the agentFile field to locate personality files. The registry is the single source of truth for who fills each role.

MANDATORY: Start with Triage — DO NOT SKIP

YOU MUST read and execute 00-delegation-and-triage.md BEFORE doing anything else.

DO NOT read source code. DO NOT edit files. DO NOT start solving the problem. The pipeline exists to ensure quality — every shortcut you take skips a review, a gate, or a verification step.

Your FIRST action must be: Read the triage doc, classify the directive weight, output the triage block, and create directive.json. Only then proceed to the next pipeline step.

Read the full file on GitHub · 135 lines

Files

What ships with it

31 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

10d ago First seen · 135 lines · 170 tokens per session scan A c664e6329d10

Subscribe to this mod's changes

directive is a skill published in the GitHub repository andrew-yangy/gru-ai (153 stars, last pushed 6mo ago), licensed MIT. It adds 170 tokens to every session and 2,705 once invoked, about $0.0009 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.

Autonomous Agents Building agents Planning ai-agents context-engineering harness-engineering

building

Implementation skill for writing production code with TDD. Covers the RED-GREEN-REFACTOR cycle, false-RED detection, vertical slicing, scope escalation, test process discipline, and code generation patterns. Loaded by component-builder and bug-investigator.

romiluz13/cc10x · 53 tokens

diff-driven-docs

Use when a BUILD phase completes, a commit is staged, or a PR is about to be created, and the diff has not yet been reflected in documentation. Also use when the user says "update docs", "sync docs", "document this", or asks whether documentation is up to date.

romiluz13/cc10x · 64 tokens

exploration

Two-mode exploration skill: (1) design dialogue — turn rough ideas into validated designs through collaborative interview before planning; (2) spike — throwaway code answering ONE design question, deleted or absorbed, never shipped. Router invokes mode via dispatch context.

romiluz13/cc10x · 56 tokens

memory-and-handoff

Two-mode skill: (1) session memory — load/persist durable workflow state under .cc10x/ (activeContext, patterns, progress) so context survives compaction; (2) handoff package — portable, secrets-redacted export for a coworker, different tool, or fresh non-cc10x session.

romiluz13/cc10x · 70 tokens

plan-review-gate

Use after saving a non-trivial plan or decision RFC when a fail-closed feasibility, completeness, and alignment review must block execution.

romiluz13/cc10x · 32 tokens

architecture

Greenfield architecture design: map functionality flows, draw components, design APIs, classify dependencies, plan observability. For multi-component, API, schema, auth, or integration-heavy work. For retrofitting existing code, use codebase-hygiene instead.