sdd-workflow

sdd-workflow is a skill for Claude Code, Codex from juanklagos/spec-driven-development-template. It costs 84 tokens per session (987 once invoked), scanned A, original, MIT.

A workflow for Spec-Driven Development, where a project is described and planned in documents before code is written. It tracks the idea, specification, tasks, approval, implementation, validation, and history.

In plain words
What is it for?
Use it to capture an idea, create and refine a specification and implementation plan, prepare tasks, record user consent, guide development, validate the result, and maintain a project logbook.
Why use it?
It prevents coding from starting with an unclear or unapproved plan. The recorded steps make decisions and progress easier to trace.

Skill for Claude CodeCodex

Part of the sdd plugin — 2 skills, 8 commands, 2 MCP servers shipped together

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 skills/juanklagos/spec-driven-development-template/sdd-workflow
Any agent
npx skills add juanklagos/spec-driven-development-template --skill sdd-workflow
Clone the repo
git clone --depth 1 https://github.com/juanklagos/spec-driven-development-template

Made for: Claude Code, Codex.

Or install sdd, the plugin that ships this one along with the rest of its 2 skills, 8 commands, 2 MCP servers.

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-workflow

README.md
[![agentmods](https://agentmods.dev/badge/skills/juanklagos/spec-driven-development-template/sdd-workflow.svg)](https://agentmods.dev/skills/juanklagos/spec-driven-development-template/sdd-workflow)
Your own site
<a href="https://agentmods.dev/skills/juanklagos/spec-driven-development-template/sdd-workflow"><img src="https://agentmods.dev/badge/skills/juanklagos/spec-driven-development-template/sdd-workflow.svg" alt="Measured on agentmods" height="20"></a>
Per session 84 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 987 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00084 $0.00987
Opus 5 $0.00042 $0.00494
Sonnet 5 $0.00017 $0.00197
Haiku 4.5 $0.00008 $0.00099

Measured 4d ago against content hash e8dc9a653b4d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

sdd-workflow 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 4d 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-workflow/SKILL.md · 51 lines

How it starts

The opening of the file, as written. The whole thing — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.

SDD Workflow / Flujo SDD

You are an SDD Pilot. Guide the user through Specification → Planning → Implementation → Validation with full traceability. Respond in the user's language (EN/ES).

Hard stop (never skip) / Parada dura (nunca la omitas)

No code before an approved spec.md and a consistent plan.md. No hay código sin spec.md aprobada y plan.md consistente.

  • Creating/refining SDD artifacts (idea, spec, plan, tasks, bitacora) needs no consent.
  • Right before implementation starts, ask for explicit user consent and record it for that spec: ./scripts/confirm-user-consent.sh --spec NNN-slug "User approved implementation for spec NNN-slug" (sidecar: ./spec/scripts/...).
  • Consent is per spec: one recorded consent opens the gate for that spec id only.

Workflow

  1. Observe: read idea/IDEA_GENERAL.md, specs/INDEX.md, and the latest bitacora/handoffs/ entry if present. In sidecar projects these live under ./spec/.
  2. Idea: capture name, problem, main goal, MVP scope in idea/IDEA_GENERAL.md.
  3. Spec: create a numbered bundle (spec.md, plan.md, tasks.md, history.md) with ./scripts/new-spec.sh "feature" "Owner". Write acceptance criteria in EARS form: WHEN [trigger], THE SYSTEM SHALL [observable behavior].
  4. Approval: the user must approve spec.md (record status, date, approver, evidence in its approval section).
  5. Plan + tasks: make plan.md consistent with the spec; break work into checklist tasks.
  6. Gate: run and pass before any implementation:
    • ./scripts/check-sdd-policy.sh .
    • ./scripts/check-sdd-gate.sh .
  7. Implement: only in-scope tasks, one active spec at a time.
  8. Record decisions: write bitacora/decisiones/YYYY-MM-DD-<slug>.md (template bitacora/templates/DECISION_TEMPLATE.md, command /sdd:decision) whenever a choice picked between real alternatives, will be expensive to reverse, or would make a future reader ask "why is it like this?" — with a "when to revisit" section and every rationale pointing at a real source (commit, file:line, spec history, CHANGELOG, idea/). Never invent rationale or dates.
  9. Validate + close: ./scripts/validate-sdd.sh . --strict; update history.md, specs/INDEX.md, bitacora/global/PROJECT_LOG.md, bitacora/diaria/YYYY-MM-DD.md.

Read the full file on GitHub · 51 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. 4d ago First seen · 51 lines · 84 tokens per session scan A e8dc9a653b4d

Subscribe to this mod's changes

sdd-workflow is a skill published in the GitHub repository juanklagos/spec-driven-development-template (15 stars, last pushed 4d ago), licensed MIT. It adds 84 tokens to every session and 987 once invoked, about $0.0004 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.