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.

agent-sdd-kit CLAUDE.md — Instructions file by erionrb

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/erionrb/agent-sdd-kit/claude-md

Clone the repo

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

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. 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	$0.00691	$0.00691
Opus 5	$0.00345	$0.00345
Sonnet 5	$0.00138	$0.00138
Haiku 4.5	$0.00069	$0.00069

Measured 2d ago against content hash 7ff00aa81701, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 2d 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.

2d 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 3mo ago), licensed Apache-2.0. It adds 691 tokens to every session, about $0.0035 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.

Code review Planning Productivity

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

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

agent-sdd-kit CLAUDE.md