sdd-full

sdd-full is a command for Claude Code from zekiriabd/SDD-Pro. It costs 19 tokens per session (10,960 once invoked), scanned A, original, Apache-2.0.

An orchestrator that runs the complete SDD workflow for one feature, from user-story creation through architecture, coding, and quality checks.

In plain words
What is it for?
Use it to generate user stories, prepare UI mockups, validate readiness, plan and review implementation, build backend and frontend code, and run quality checks.
Why use it?
It removes the need to start each development phase manually and pauses for human review when the plan needs approval.

Command for Claude Code

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 commands/zekiriabd/sdd-pro/sdd-full
Clone the repo
git clone --depth 1 https://github.com/zekiriabd/SDD-Pro

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.

agentmods badge for sdd-full

README.md
[![agentmods](https://agentmods.dev/badge/commands/zekiriabd/sdd-pro/sdd-full.svg)](https://agentmods.dev/commands/zekiriabd/sdd-pro/sdd-full)
Your own site
<a href="https://agentmods.dev/commands/zekiriabd/sdd-pro/sdd-full"><img src="https://agentmods.dev/badge/commands/zekiriabd/sdd-pro/sdd-full.svg" alt="Measured on agentmods" height="20"></a>
Per session 19 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 10,960 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 5.1 $0.00019 $0.10960
Opus 5 $0.00010 $0.05480
Sonnet 5 $0.00004 $0.02192
Haiku 4.5 $0.00002 $0.01096

Measured 6d ago against content hash 61b5cbea9009, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

sdd-full 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 6d 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/commands/sdd-full.md · 856 lines

How it starts

The opening of the file, as written. The whole thing — 856 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/sdd-full — Pipeline complet de A à Z pour 1 FEAT

Enchaîne toutes les phases du pipeline SDD pour la FEAT {n} :

PHASE 2    — US generation         (agent po, via /us-generate)
PHASE 2.5  — HTML mockups          (humain — workspace/ui/, pas d'agent)
PHASE 2.6  — Readiness gate        (Python déterministe v6, via /feat-validate)
PHASE 2.7  — Plan-then-review gate (mode :plan, via /dev-plan, conditionnel)
PHASE 3    — ARCH + DB             (agent arch, via /dev-run)
PHASE 4    — CODE back+front       (agents dev-*, via /dev-run, parallèle)
PHASE 5    — QA + Quality          (agent qa, via /qa-generate, conditionnel)

Délégation pure : /sdd-full n'invoque AUCUN agent directement — elle chaîne /us-generate/feat-validate → (/dev-plan) → /dev-run → (/qa-generate).

Checkpoint humain : un seul, au STEP 3.6 (review des plans), et uniquement si readiness ≠ GO ou si --plan activé.


⚡ Orchestrateur Python (pattern recommandé)

Mode thin-wrapper : piloter le pipeline via sdd_full_planner.py (33 tests verts) au lieu d'interpréter les 19 STEPs ci-dessous. Substance décisionnelle en code testable, spawns LLM en Markdown. Les STEPs restent valides comme spec step-by-step + backward-compat.

# 1. Build plan (0 token, ~50ms)
python .sdd/python/sdd_scripts/sdd_full_planner.py plan \
  --feat-number {n} --json > workspace/.sys/.state/plan-{n}.json

# 2. Init state
RUN_ID=$(python .sdd/python/sdd_scripts/sdd_state.py new-run \
  --feat-number {n} --command "/sdd-full" --tags "$TAGS")

# 3. Boucle next-action jusqu'à action ∈ {done, stop}
while true; do
  STATE='{"completed_phases":[...],"last_status":"...","last_verdict":"...","flags":{...}}'
  DECISION=$(python .sdd/python/sdd_scripts/sdd_full_planner.py next-action \
    --plan-json workspace/.sys/.state/plan-{n}.json --state-inline "$STATE")
  ACTION=$(echo "$DECISION" | jq -r '.action')
  case "$ACTION" in
    skill)  SKILL=$(echo "$DECISION" | jq -r '.skill') ;;  # tool call Claude
    script) SCRIPT=$(echo "$DECISION" | jq -r '.script'); ARGS=$(echo "$DECISION" | jq -r '.args[]'); python "$SCRIPT" $ARGS ;;
    skip)   ;;  # marker completed et continue
    stop|done) break ;;
  esac
done

# 4. Recap (lit state.json + console.db)
python .sdd/python/sdd_scripts/sdd_full_planner.py recap --run-id "$RUN_ID"

Read the full file on GitHub · 856 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. 6d ago First seen · 856 lines · 19 tokens per session scan A 61b5cbea9009

Subscribe to this mod's changes

sdd-full is a command published in the GitHub repository zekiriabd/SDD-Pro (191 stars, last pushed 2d ago), licensed Apache-2.0. It adds 19 tokens to every session and 10,960 once invoked, about $0.0001 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.