A local spec-driven development command that turns an approved product requirement into an implementation and testing loop. A product requirement describes what should be built and how success will be checked.

Use it to plan a feature, iterate between coding and testing, evaluate whether the specification is satisfied, and prepare the work for a later pull request.

It keeps development tied to explicit acceptance criteria and stops when the required behavior is not sufficiently specified or approved.

sdd — Command by Pierry

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/pierry/harness-kit/sdd

Clone the repo

git clone --depth 1 https://github.com/Pierry/harness-kit

Made for: Claude Code.

Per session 29 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,099 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.

Model	Per session	Once invoked
Fable 5	$0.00029	$0.01099
Opus 5	$0.00015	$0.00549
Sonnet 5	$0.00006	$0.00220
Haiku 4.5	$0.00003	$0.00110

Measured 2d ago against content hash 731b28a7135a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

sdd 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/commands/sse/sdd.md · 102 lines

How it starts

The opening of the file, as written. The whole thing — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Run spec-driven dev loop. Follow .claude/agents/staff-software-engineer/guides/sdd-loop.md.

Inputs

Optional arg: path to source PRP. Default = latest approved PRP in .claude/runtime/outputs/pm/prp/.
None found → abort. Tell user to run /product-manager:prp first.

feature_id = basename of PRP file (no .md).

Pre-flight (hard gate)

Run sensor .claude/agents/staff-software-engineer/sensors/prp-has-acceptance-criteria.md on source PRP. Fail → block, return blocker. Do not proceed.

Print header card. Format: .claude/scripts/stage-card.md.

━━━ /sse:sdd · {feature_id} ━━━
**guides:**  sdd-loop.md, pipeline.md
**refs:**    prp/{feature_id}.md
**sensors:** prp-has-acceptance-criteria
**eval:**    spec-satisfied (supervisor, per iter)
**next:**    /sse:pr (after PASS, manual trigger)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

Steps

Plan once. Invoke /sse:plan. Wait approved marker. Hard stop if plan fails.
Goal loop. Cap = 3 iters.

For iter in 1..3:

a. Write the iter start marker via the committed script (do NOT inline date/printf):
```
.claude/scripts/marker.sh start .claude/runtime/outputs/sse/.markers/{feature_id}.sdd-iter{N}-dev.start
```
b. Invoke /sse:dev. If iter > 1, pass --focus="{next_iter_focus from prior eval}". c. Invoke /sse:test. Capture report path. d. Run supervisor eval .claude/agents/staff-software-engineer/evals/spec-satisfied.md. Use fresh session (Task tool with subagent_type=general-purpose, prompt includes PRP path + dev summary path + test report path + git diff main...HEAD). Worker context must not leak. e. Parse eval JSON output. Verdict PASS → break. FAIL → record next_iter_focus, continue.
Write transcript .claude/runtime/outputs/sse/sdd/{feature_id}.md. Format per guides/sdd-loop.md § Output artifact.

PASS path: append approval marker:

<!-- approved: {YYYY-MM-DD} verdict=PASS iters={N} -->

FAIL path (cap hit): append:
```

```
Return blocker listing NOT_MET criteria + UNCLEAR items.

Read the full file on GitHub · 102 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 · 102 lines · 29 tokens per session scan A 731b28a7135a

Subscribe to this mod's changes

sdd is a command published in the GitHub repository Pierry/harness-kit (3 stars, last pushed 1mo ago), licensed MIT. It adds 29 tokens to every session and 1,099 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 2026-08-31.

Code review Planning Testing agentic-workflows ai-agents ai-tools anthropic claude claude-code

sdd

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

Inputs

Pre-flight (hard gate)

Steps

What this file has done since we first saw it

Other commands, from other repositories

setup-pm-skills

statusbar-style

fest-show

superpowers-execute

config

deps-age