stepwise-dev: Instructions file for Claude Code

AGENTS.md

stepwise-dev AGENTS.md is an instructions file for Claude Code, Codex, OpenCode from nikeyes/stepwise-dev. It costs 2,878 tokens per session, scanned A, original, Apache-2.0.

Repository instructions for agents working on Stepwise Dev, a local workflow project for coding agents. They describe its plugins, skills, specialized agents, scripts, and research-to-validation process.

In plain words
What is it for?
They are for understanding the multi-plugin layout and working with the project's research, planning, implementation, validation, and thoughts-storage tools.
Why use it?
They give agents a shared source of truth so changes follow the repository's structure and development workflow.

Instructions file for Claude CodeCodexOpenCode

Written for Claude Code and Codex and OpenCode: ${CLAUDE_PLUGIN_ROOT variable, but also reads ~/.codex or $CODEX_HOME. Also seen: mentions CLAUDE.md; mentions Claude Code; mentions AGENTS.md.

This is nikeyes/stepwise-dev's own configuration. It tells Claude Code, Codex and OpenCode how to work on stepwise-dev 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 stepwise-dev configures →

Runs only inside a plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else, and the catalogue could not identify which plugin ships it.

Reuse

Borrowing it

Nothing to install: this file belongs to nikeyes/stepwise-dev. 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/nikeyes/stepwise-dev/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/nikeyes/stepwise-dev

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 stepwise-dev AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/nikeyes/stepwise-dev/agents-md.svg)](https://agentmods.dev/instructions/nikeyes/stepwise-dev/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/nikeyes/stepwise-dev/agents-md"><img src="https://agentmods.dev/badge/instructions/nikeyes/stepwise-dev/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 2,878 This file is loaded in full into every session.
When invoked 2,878 The same file — it is already loaded in full.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.02878 $0.02878
Opus 5 $0.01439 $0.01439
Sonnet 5 $0.00576 $0.00576
Haiku 4.5 $0.00288 $0.00288

Measured yesterday against content hash 4c9ae2c3d4a4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

stepwise-dev 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 yesterday.

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 · 320 lines

How it starts

The opening of the file, as written. The whole thing — 320 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

This file is the source of truth for coding agents working in this repository. CLAUDE.md is a one-line pointer to it, so Claude Code and OpenAI Codex read the same guidance.

Repository Overview

This is a workflow tooling project for Claude Code itself, not a traditional software application. It provides skills, specialized agents, and bash scripts that implement a structured Research → Plan → Implement → Validate development cycle.

The workflow operates entirely locally without cloud dependencies and uses a thoughts/ directory system for persistent storage.

Multi-Plugin Architecture

This project is distributed as 4 independent Claude Code plugins in a single marketplace:

Plugin 1: stepwise-core

Location: core/ Components:

  • 11 skills (research-codebase, create-plan, iterate-plan, implement-plan, validate-plan, thoughts-management, bugmagnet, grill-me, tdd, hamburger-method, small-safe-steps, story-splitting, test-desiderata)
  • 5 specialized agents (codebase-locator, codebase-analyzer, codebase-pattern-finder, thoughts-locator, thoughts-analyzer)

Plugin 2: stepwise-git

Location: git/ Components:

  • 2 skills (commit, review-pr-comments)

Plugin 3: stepwise-web

Location: web/ Components:

  • 1 specialized agent (web-search-researcher)

Plugin 4: stepwise-research

Location: research/ Components:

  • 1 skill (deep-research, includes generate-report script)
  • 3 specialized agents (research-lead, research-worker, citation-analyst)

Installation:

# Add marketplace
claude plugin marketplace add [email protected]:nikeyes/stepwise-dev.git

# Install all (or pick individual ones)
claude plugin install stepwise-core@stepwise-dev
claude plugin install stepwise-git@stepwise-dev
claude plugin install stepwise-web@stepwise-dev
claude plugin install stepwise-research@stepwise-dev

See README.md for detailed installation instructions.

Project Structure

.claude-plugin/        # Marketplace configuration
└── marketplace.json   # Marketplace listing all 4 plugins

core/                  # stepwise-core plugin
├── .claude-plugin/
│   └── plugin.json
├── agents/            # 5 specialized agents (markdown files)
│   ├── codebase-locator.md
│   ├── codebase-analyzer.md
│   ├── codebase-pattern-finder.md
│   ├── thoughts-locator.md
│   └── thoughts-analyzer.md
└── skills/            # 11 skills (SKILL.md directories)
    ├── create-plan/SKILL.md
    ├── iterate-plan/SKILL.md
    ├── implement-plan/SKILL.md
    ├── validate-plan/SKILL.md
    ├── research-codebase/SKILL.md
    ├── thoughts-management/
    │   ├── SKILL.md
    │   └── scripts/
    │       ├── thoughts-init
    │       └── thoughts-metadata
    ├── bugmagnet/SKILL.md
    ├── hamburger-method/SKILL.md
    ├── small-safe-steps/SKILL.md
    ├── story-splitting/SKILL.md
    └── test-desiderata/SKILL.md

git/                   # stepwise-git plugin
├── .claude-plugin/
│   └── plugin.json
└── skills/            # 2 skills
    ├── commit/SKILL.md
    └── review-pr-comments/SKILL.md

web/                   # stepwise-web plugin
├── .claude-plugin/
│   └── plugin.json
└── agents/            # 1 specialized agent
    └── web-search-researcher.md

research/              # stepwise-research plugin
├── .claude-plugin/
│   └── plugin.json
├── agents/            # 3 specialized agents
│   ├── research-lead.md
│   ├── research-worker.md
│   └── citation-analyst.md
└── skills/            # 1 skill
    └── deep-research/
        ├── SKILL.md
        └── scripts/
            └── generate-report

codex/                 # OpenAI Codex compatibility layer
├── agents/*.toml      # 9 generated agent definitions
├── transpile-agents.sh
├── install.sh
└── uninstall.sh

test/                  # Automated bash tests (for development)

Read the full file on GitHub · 320 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. yesterday First seen · 320 lines · 2,878 tokens per session scan A 4c9ae2c3d4a4

Subscribe to this mod's changes

stepwise-dev AGENTS.md is an instructions file published in the GitHub repository nikeyes/stepwise-dev (24 stars, last pushed 2d ago), licensed Apache-2.0. It adds 2,878 tokens to every session, about $0.0144 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 2026-09-05.

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 · 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 · 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

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

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

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