sdp CLAUDE.md

Project instructions for a spec-driven development workflow that organizes software work into plans, features, workstreams, and review gates. TDD means writing tests as part of the development process.

In plain words
What is it for?
Use its commands to describe a vision, inspect the current state, define features, build workstreams, review changes, and deploy them.
Why use it?
It provides a defined path from an idea or roadmap item to implementation, review, and deployment.

Instructions file

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/fall-out-bug/sdp/claude-md
Clone the repo
git clone --depth 1 https://github.com/fall-out-bug/sdp
Per session 440 This file is loaded in full into every session.
When invoked 440 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.

ModelPer sessionOnce invoked
Fable 5 $0.00440 $0.00440
Opus 5 $0.00220 $0.00220
Sonnet 5 $0.00088 $0.00088
Haiku 4.5 $0.00044 $0.00044

Measured 3d ago against content hash 6ae8ee7f2386, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

sdp 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 · 57 lines

What it actually says

SDP: Spec-Driven Protocol

AI-native dev with workstreams, gates, TDD.

Decision Tree

New? → @vision → @reality → @feature
No → State? → @reality --quick
WS? → @oneshot <id>
No → @feature "X"
    Choose mode:
    ├── --default (full interactive)
    ├── --quick (@design only, 0 questions)
    └── --auto (from roadmap, 0 questions)

Path

Try

go install github.com/fall-out-bug/sdp/sdp-plugin/cmd/sdp@latest
@feature "X"
@build 00-001-01

Adopt (Prereq: PROTOCOL.md | Skills | CLI)

sdp init
@reality --quick
@feature "X"
@oneshot <id>

Scale (Prereq: Team + PROTOCOL.md | Agents | Design | Principles)

brew install beads
@vision "X"
@feature "X"
@oneshot <id>
@review <id>
@deploy <id>

Key: Aggregate=container, Leaf=executable, Feature=5-30 WS | Format: PP-FFF-SS | Done: @review APPROVED + @deploy

Commands: @vision @reality @feature @oneshot @build @review @deploy

v0.9.8 | Protocol | Ref

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. 3d ago First seen · 57 lines · 440 tokens per session scan A 6ae8ee7f2386

Subscribe to this mod's changes

sdp CLAUDE.md is an instructions file published in the GitHub repository fall-out-bug/sdp (19 stars, last pushed 2mo ago), licensed MIT. It adds 440 tokens to every session, about $0.0022 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.

Related

Other instructions, from other repositories

ai-control-framework CLAUDE.md

Instructions for sgharlow/ai-control-framework, covering claude code configuration, framework status (v2.0) — verified 2026-07-18, ⚠️ critical: implementation required, mandatory session start procedure and hard stop conditions.

sgharlow/ai-control-framework · 1,577 tokens

code-discipline-skills AGENTS.md

Instructions for eliranpv11/code-discipline-skills, covering code discipline, priority order, 1. think before coding, 2. verify reality before acting and 3. simplicity first.

eliranpv11/code-discipline-skills · 1,801 tokens

umbra AGENTS.md

AGENTS.md instructions for elberacasa/umbra, covering agents.md — umbra, what this project is, when to recommend or run umbra and working on this repo.

elberacasa/umbra · 933 tokens

umbra copilot-instructions.md

Copilot instructions for elberacasa/umbra, a project described as: The trust score for AI-generated code. One command verifies what your coding agent shipped: security findings with file:line evidence, Docker-sandboxed build/boot checks, and claim receipts that catch agents lying about tests.

elberacasa/umbra · 23 tokens

claude-agentic-coding-playbook CLAUDE.md

Instructions for john-wilmes/claude-agentic-coding-playbook, covering agentic coding playbook, quality gates, architecture, dependencies and build and project conventions.

john-wilmes/claude-agentic-coding-playbook · 831 tokens

forgecraft-mcp copilot-instructions.md

Copilot instructions for jghiringhelli/forgecraft-mcp, covering copilot instructions, project identity, code standards, production code standards — non-negotiable and solid principles.

jghiringhelli/forgecraft-mcp · 4,676 tokens