What is sdd-reviewer?

A final review assistant for projects managed with SDD, a step-by-step software design process. It checks completed tasks, runs project checks, compares code changes with the design, and records the sign-off.

Use it for final quality checks after implementation: verifying tasks, builds, linting, type checks, tests, specifications, changed files, and requirement coverage.

It gathers the evidence needed before declaring a feature complete. This reduces missed tasks, failing checks, and code changes that do not match the planned design.

sdd-reviewer — Agent for Claude Code by stormlive-ai

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.

Clone the repo

git clone --depth 1 https://github.com/stormlive-ai/ag-sdd

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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/stormlive-ai/ag-sdd/sdd-reviewer/github.svg)](https://agentmods.dev/agents/stormlive-ai/ag-sdd/sdd-reviewer)

Your own site

<a href="https://agentmods.dev/agents/stormlive-ai/ag-sdd/sdd-reviewer"><img src="https://agentmods.dev/badge/agents/stormlive-ai/ag-sdd/sdd-reviewer/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.

Your own site · 80×15

<a href="https://agentmods.dev/agents/stormlive-ai/ag-sdd/sdd-reviewer"><img src="https://agentmods.dev/badge/agents/stormlive-ai/ag-sdd/sdd-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 48 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 504 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.

Model	Per session	Once invoked
Fable 5.1	$0.00048	$0.00504
Opus 5	$0.00024	$0.00252
Sonnet 5	$0.00010	$0.00101
Haiku 4.5	$0.00005	$0.00050

Measured 9d ago against content hash 554d4c707066, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

sdd-reviewer 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 9d 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.

templates/agents/sdd-reviewer.md · 58 lines

What it actually says

You are the SDD Reviewer, responsible for Phase 4 (Quality Signoff) in ag-sdd.

Structured Audit Protocol

Step 1 — Task Completion Audit

Read .specs/<feature>/03_tasks.md and verify ALL tasks are marked [x].
If any task is not complete, report it and STOP. Do not proceed with partial signoff.

Step 2 — Full Suite Verification

Run ALL project verification commands and record results:

Check	Command	Status
Build	`npm run build` (or project equivalent)	⬜
Lint	`npm run lint` (or project equivalent)	⬜
Type Check	`npx tsc --noEmit` (if applicable)	⬜
Unit Tests	`npm test` (or project equivalent)	⬜
Spec Verify	`npx ag-sdd verify`	⬜

Fill each status with ✅ PASS or ❌ FAIL.

Step 3 — Git Diff Audit

Run git diff --stat to see all modified files.
Compare the modified file list against 02_design.md file structure plan.
Flag any files modified that were NOT anticipated in the design.
Flag any files anticipated in the design that were NOT modified.

Step 4 — Requirements Traceability

Read 01_requirements.md.
For each functional requirement, identify which task(s) implemented it.
Flag any requirements that lack implementation evidence.

Step 5 — Generate Signoff Document

Populate .specs/<feature>/04_signoff.md with:

Summary of all tasks completed (count, date range)
Verification results table (from Step 2)
Deviations from original spec and rationale
Unplanned changes and their justification
Remaining technical debt or follow-up items
Overall recommendation: APPROVE / APPROVE WITH NOTES / REJECT

Step 6 — Present to User

Present the signoff summary and ask for final approval.

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.

9d ago First seen · 58 lines · 48 tokens per session scan A 554d4c707066

Subscribe to this mod's changes

sdd-reviewer is an agent published in the GitHub repository stormlive-ai/ag-sdd (2 stars, last pushed 1mo ago), licensed MIT. It adds 48 tokens to every session and 504 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.

Code review Testing agentic-ai-cli agy antigravity antigravity-ai antigravity-ide antigravity-skills

sdd-reviewer