What is agent-sdd-kit CLAUDE.md?

Repository instructions for agent-sdd-kit, a toolkit that helps teams plan and build software through written steps. SDD means specification-driven development: describe the change, define expected behavior, design it, list tasks, then implement and review it.

Use it to explore a problem, create a proposal and specifications, apply implementation tasks, check change status, and archive completed work.

It gives coding agents a consistent process and commands for turning an idea into checked implementation work. It also explains where change documents are stored and how to track them.

How erionrb/agent-sdd-kit configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to erionrb/agent-sdd-kit. 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/erionrb/agent-sdd-kit/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/erionrb/agent-sdd-kit

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/instructions/erionrb/agent-sdd-kit/claude-md/github.svg)](https://agentmods.dev/instructions/erionrb/agent-sdd-kit/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/erionrb/agent-sdd-kit/claude-md"><img src="https://agentmods.dev/badge/instructions/erionrb/agent-sdd-kit/claude-md/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/instructions/erionrb/agent-sdd-kit/claude-md"><img src="https://agentmods.dev/badge/instructions/erionrb/agent-sdd-kit/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 691 This file is loaded in full into every session.

When invoked 691 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.

Model	Per session	Once invoked
Fable 5.1	$0.00691	$0.00691
Opus 5.5	$0.00276	$0.00276
Sonnet 5.5	$0.00138	$0.00138
Haiku 4.5	$0.00069	$0.00069

Measured 2mo ago against content hash 7ff00aa81701, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

agent-sdd-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 2mo 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 · 73 lines

How it starts

The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Purpose

This is agent-sdd-kit — an open source SSD/SDD AI workflow toolkit and the canonical setup provider for applying the SDD methodology to real software repositories. It is not a product codebase; it is the tooling, training, prompt, and setup layer reused across projects.

Workflow

All development in this repo follows the SDD cycle via OpenSpec CLI (v1.3.1):

Idea → proposal.md (what/why) → specs.md → design.md (how) → tasks.md (steps) → implement → review → QA

Key commands

# Start a new change (interactive — generates all artifacts)
/opsx:propose

# Implement tasks from an existing change
/opsx:apply

# Explore / think through a problem before proposing
/opsx:explore

# Archive a completed change into main specs
/opsx:archive

# CLI equivalents
openspec new change <name>         # scaffold a new change
openspec status --change <name>    # check artifact completion
openspec list                      # list all active changes
openspec instructions apply --change <name> --json  # get implementation instructions

Changes live in openspec/changes/<name>/ with .openspec.yaml and artifact files (proposal.md, specs.md, design.md, tasks.md).

The active schema is spec-driven: proposal → specs → design → tasks. Config is at openspec/config.yaml.

Structure

.claude/skills/         OpenSpec skills for Claude Code (opsx:propose, apply, explore, archive)
.cursor/skills/         Same skills mirrored for Cursor
docs/training/path/     8-step SDD learning path (start at README.md)
openspec/               OpenSpec project root (config + future changes/)
memory/                 Persistent memory for Claude Code sessions

What's missing (build these next)

The framework is partially set up. The docs/training/path/08-whats-next.md file has the full action checklist. Short version:

docs/context/architecture.md — system/stack overview agents read before coding
docs/context/thinking-model.md — how to analyze problems and assess change impact
docs/context/coding-conventions.md — naming, structure, style rules
PRD generator skill (interactive, asks clarifying questions)
Tech Pack generator skill (uses Context7 MCP for library docs)
Task Reviewer skill (spawned as a sub-agent after each task)
QA runner skill (Playwright e2e + accessibility)
Bug Fix skill (reads QA bug report, applies fixes)

Read the full file on GitHub · 73 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.

2mo ago First seen · 73 lines · 691 tokens per session scan A 7ff00aa81701

Subscribe to this mod's changes

agent-sdd-kit CLAUDE.md is an instructions file published in the GitHub repository erionrb/agent-sdd-kit (3 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 691 tokens to every session, about $0.0028 per session on Opus 5.5. 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.

Planning

agent-sdd-kit CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
agent-sdd-kit CLAUDE.mderionrb/agent-sdd-kit	Instructions file	3	5mo ago	Apache-2.0	A	691	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

agent-sdd-kit: Instructions file for Claude Code