sdd-flow

sdd-flow is a skill for Claude Code from contactandrewchl-wq/turtle-mcp. It costs 44 tokens per session (3,633 once invoked), scanned A, original, MIT.

A software-development workflow that defines requirements, design, implementation steps, links each decision to a requirement, and checks the result against it. SDD means specification-driven development: writing the specification before building.

In plain words
What is it for?
Planning new features or modules, formalising API or business rules, coordinating work across multiple pull requests or agents, and checking that delivered code matches its requirements.
Why use it?
It reduces confusion about what a feature should do and makes larger changes easier to plan, review, and verify.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions Codex; mentions OpenCode.

Part of the turtle plugin — 26 skills shipped together

Good fit Planning new features or modules, formalising API or business rules, coordinating work across multiple pull requests or agents, and checking that delivered code matches its requirements.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/contactandrewchl-wq/turtle-mcp/sdd-flow
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.

Any agent
npx skills add contactandrewchl-wq/turtle-mcp --skill sdd-flow
Clone the repo
git clone --depth 1 https://github.com/contactandrewchl-wq/turtle-mcp

Made for: Claude Code.

Or install turtle, the plugin that ships this one along with the rest of its 26 skills.

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 sdd-flow

README.md
[![agentmods](https://agentmods.dev/badge/skills/contactandrewchl-wq/turtle-mcp/sdd-flow/github.svg)](https://agentmods.dev/skills/contactandrewchl-wq/turtle-mcp/sdd-flow)
Your own site
<a href="https://agentmods.dev/skills/contactandrewchl-wq/turtle-mcp/sdd-flow"><img src="https://agentmods.dev/badge/skills/contactandrewchl-wq/turtle-mcp/sdd-flow/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.

agentmods 80×15 button for sdd-flow

Your own site · 80×15
<a href="https://agentmods.dev/skills/contactandrewchl-wq/turtle-mcp/sdd-flow"><img src="https://agentmods.dev/badge/skills/contactandrewchl-wq/turtle-mcp/sdd-flow.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 44 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,633 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00044 $0.03633
Opus 5 $0.00022 $0.01817
Sonnet 5 $0.00009 $0.00727
Haiku 4.5 $0.00004 $0.00363

Measured 12d ago against content hash 05e247296616, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

sdd-flow 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 12d 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.

skills/sdd-flow/SKILL.md · 180 lines

How it starts

The opening of the file, as written. The whole thing — 180 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Flujo SDD (desarrollo dirigido por especificación)

El desarrollo dirigido por especificación (SDD) ancla cada línea de código a un requisito explícito, verificable y trazable. La especificación precede al diseño, el diseño al plan y el plan a la implementación. Nada se construye sin una entrada que lo justifique y un criterio que pruebe que está completo.

Cuándo usar

Usa SDD cuando:

  • Arrancas una feature o módulo nuevo cuyo comportamiento aún no está formalizado.
  • Vas a planificar antes de implementar (más de un PR, dependencias entre tareas, varios agentes involucrados).
  • Necesitas formalizar o renegociar requisitos (contrato de API, reglas de negocio, criterios de aceptación).
  • El cambio tiene impacto transversal (datos, seguridad, contratos públicos) y exige trazabilidad entre sesiones.

NO uses el flujo SDD completo cuando:

  • Es un fix trivial (typo, ajuste de copy, corrección de un bug aislado con causa evidente).
  • El cambio no altera requisitos ni contratos y cabe en un solo PR pequeño.
  • Es trabajo exploratorio descartable (spike) que no llega a producción.

Regla práctica: si el cambio modifica QUÉ hace el sistema, necesita spec; si solo corrige CÓMO lo hace sin cambiar el comportamiento observable, basta con disciplina de commit ([[commit-hygiene]]).

Estándares de referencia

Estándar Qué gobierna
ISO/IEC/IEEE 29148:2018 Ingeniería de requisitos y estructura del SRS (especificación de requisitos de software).
IEEE 1016 Software Design Descriptions (SDD): cómo se documenta el diseño y sus vistas.
IEEE 1012 Verificación y Validación (V&V): qué se verifica, cómo y con qué evidencia.
ISO/IEC/IEEE 29119 Testing de software: procesos, técnicas de diseño de pruebas y documentación de casos.
ISO/IEC/IEEE 12207 Procesos del ciclo de vida del software: marco que encuadra y conecta las fases.

Fases

El flujo es lineal con compuertas (gates): no se pasa a la fase siguiente hasta cumplir el criterio de salida de la actual.

Read the full file on GitHub · 180 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. 12d ago First seen · 180 lines · 44 tokens per session scan A 05e247296616

Subscribe to this mod's changes

sdd-flow is a skill published in the GitHub repository contactandrewchl-wq/turtle-mcp (2 stars, last pushed 2mo ago), licensed MIT. It adds 44 tokens to every session and 3,633 once invoked, about $0.0002 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.

Related

Other skills, from other repositories

gno

Search local documents, files, notes, and knowledge bases. Index directories, search with BM25/vector/hybrid, get AI answers with citations. Use when user wants to search files, find documents, query notes, look up information in local folders, index a directory, set up document search, build a knowledge base, needs…

gmickel/gno · 86 tokens

engram-memory

Give the agent durable, local memory with engram — recall past decisions before answering, and persist new decisions, preferences and facts as they happen. Use when work spans sessions or the user says "remember".

jnMetaCode/skillet · 45 tokens

simplicio-loop

Unified public entrypoint for Simplicio's body-of-work orchestration: core + loop in one command. Use when the user types /simplicio-loop, says "ralph loop", "keep iterating until done", "finish all open issues", or asks to drain a queue of work autonomously. Runtime-agnostic: binds a real stop-hook where the host…

wesleysimplicio/simplicio · 120 tokens

simplicio-nest-gate

N-Nest protocol — multi-level gate-corrected agent tree. PRIME depth verification, BH port.port.port addressing, per-level confabulation catch.

wesleysimplicio/simplicio · 39 tokens

simplicio-orient

Terminal-first execution — answer facts with the shell, never with the LLM. Use whenever a step needs a fact about the filesystem, git, processes, or system resources, or runs a build/test/lint/diff whose output would flood context. Substitutes deterministic shell/CLI calls for native LLM operations and clamps their…

wesleysimplicio/simplicio · 119 tokens

simplicio-autoresearch

Evolutionary optimize-by-metric loop — mutate a target, evaluate against fixed criteria, KEEP if the score improves (commit) or REVERT if it doesn't (git checkout), repeat, plateau-break after N stagnated runs. Adapts Karpathy's autoresearch pattern (and the ECC autoresearch-agent) with mandatory yool guardrails (§11…

wesleysimplicio/simplicio · 0 tokens