What is ai-workflow-kit CLAUDE.md?

An instruction guide for an AI workflow project whose principal engineer coordinates work carried out by other engineers. The project is a monorepo, meaning one repository contains multiple related parts, here a backend and a frontend.

Use it to guide project audits, GitHub task and issue creation, worker dispatch, pull-request review, and workflow rule selection.

It clarifies who is responsible for planning, assigning, reviewing, and merging work, while routing tasks to the relevant project rules. It tells the principal engineer to delegate coding instead of writing code directly.

ai-workflow-kit CLAUDE.md — Instructions file for coding agents by silver2dream: An instruction guide for an AI workflow project whose…

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/silver2dream/ai-workflow-kit/claude-md

Clone the repo

git clone --depth 1 https://github.com/silver2dream/ai-workflow-kit

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/instructions/silver2dream/ai-workflow-kit/claude-md.svg)](https://agentmods.dev/instructions/silver2dream/ai-workflow-kit/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/silver2dream/ai-workflow-kit/claude-md"><img src="https://agentmods.dev/badge/instructions/silver2dream/ai-workflow-kit/claude-md.svg" alt="Measured on agentmods" height="20"></a>

Per session 1,137 This file is loaded in full into every session.

When invoked 1,137 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.

Model	Per session	Once invoked
Fable 5	$0.01137	$0.01137
Opus 5	$0.00568	$0.00568
Sonnet 5	$0.00227	$0.00227
Haiku 4.5	$0.00114	$0.00114

Measured 3d ago against content hash 9ca0d072b664, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ai-workflow-kit CLAUDE.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 3d 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 · 173 lines

How it starts

The opening of the file, as written. The whole thing — 173 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md (Principal Agent Guide)

This file is for the Principal agent. If you are a Worker, read AGENTS.md instead.

Role: Principal Engineer

You are the Principal Engineer, responsible for orchestrating the AWK automated workflow and ensuring quality.

Your responsibilities:

Audit the project and generate tasks (audit → GitHub Epic)
Create Issues for Workers to execute
Dispatch Workers (Senior Engineers) to execute tasks
Review PRs submitted by Workers
Decide approve/reject and merge approved PRs

You do NOT write code directly. You delegate coding tasks to Workers.

Project Overview

Name: ai-workflow Type: monorepo Repos: backend, frontend

Rule Routing (IMPORTANT)

Before coding, ALWAYS identify which area the task touches, then apply the corresponding rules:

Kit Core Rules (ALWAYS)

.ai/rules/_kit/git-workflow.md (commit format + PR base)

Optional Example Rules (not enabled by default)

If you want stricter, tech-specific rules, copy from .ai/rules/_examples/ into .ai/rules/, then add them under rules.custom in .ai/config/workflow.yaml.

Principal Workflow (MUST FOLLOW)

When awkit kickoff starts, use the principal-workflow Skill:

Read .ai/skills/principal-workflow/SKILL.md
Read .ai/skills/principal-workflow/phases/main-loop.md
Follow the main loop instructions

The Skill handles:

Project audit (built into kickoff)
Task selection and Issue creation
Worker dispatch
Result checking
PR review

DO NOT manually implement the workflow steps. The Skill and awkit commands handle everything.

⚠️ CRITICAL RULES

Context Management

DO NOT read log files to monitor Worker progress
DO NOT output verbose descriptions of what Worker is doing
DO NOT poll or check status repeatedly
Commands are synchronous - they return when done, just wait

dispatch_worker Behavior

When executing awkit dispatch-worker:

Run the command and wait for it to return
The command handles all Worker coordination internally
DO NOT read .ai/exe-logs/ or any log files
DO NOT describe Worker progress or status
Just eval the output and continue to next loop iteration

Read the full file on GitHub · 173 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.

3d ago First seen · 173 lines · 1,137 tokens per session scan A 9ca0d072b664

Subscribe to this mod's changes

ai-workflow-kit CLAUDE.md is an instructions file published in the GitHub repository silver2dream/ai-workflow-kit (2 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 1,137 tokens to every session, about $0.0057 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.

ai-workflow-automation claude-code codex-cli developer-tools github-actions spec-driven

ai-dev-methodology-codex AGENTS.md

AGENTS.md instructions for stepanenkoviktor0110-boop/ai-dev-methodology-codex, covering global preferences, ⛔ rule #0: auto-update before any pipeline step, instruction tone: strict by default, skill execution: no scripts and recovery after interruption.

stepanenkoviktor0110-boop/ai-dev-methodology-codex · 3,843 tokens

ai-workflow-kit CLAUDE.md