Getting it into your agent
There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.
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.
[](https://agentmods.dev/commands/dinhnguyenngoc/spec-driven-claude-code/review)<a href="https://agentmods.dev/commands/dinhnguyenngoc/spec-driven-claude-code/review"><img src="https://agentmods.dev/badge/commands/dinhnguyenngoc/spec-driven-claude-code/review.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00015 | $0.03679 |
| Opus 5 | $0.00008 | $0.01840 |
| Sonnet 5 | $0.00003 | $0.00736 |
| Haiku 4.5 | $0.00002 | $0.00368 |
Grade A, and why
review 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.
How it starts
The opening of the file, as written. The whole thing — 187 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/review — Code Review
"Quality is non-negotiable."
Purpose
Perform a thorough code review of specified files, branch changes, or a pull request using the Five-Axis Framework (Correctness, Readability, Architecture, Security, Performance).
Workspace Mode: if the session root declares
Mode: workspace→ resolve the target repo perCLAUDE.md§Workspace Mode before anything else; every path, probe, and gate below is relative to the target repo, and the workspace disk-check applies at the gate.
Prerequisites
- Code implementation complete (
/builddone) - Tests passing (
/testdone) - Code compiles without errors (
dotnet build)
Inputs
The reviewer MUST ingest these artifacts before scoring. A finding without traceability back to one of them cannot satisfy the Relates-to requirement and will fail Gate 7. (Brownfield: ingest only what the diff relates-to — see §Brownfield Mode.)
| Artifact | Used to verify |
|---|---|
specs/SPEC.md + specs/user-stories/* |
Correctness — does the implementation match each US-XXX acceptance criterion? |
architecture/adr/*.md + architecture/api/* |
Architecture — are ADR decisions honored? Do API contracts match the implemented routes/DTOs? |
plans/todo.md |
Scope — did /build close exactly the tasks it claimed (Task N.N)? Flag orphan changes or unticked tasks. |
plans/plan.md §Impact Analysis |
Blast radius — diff the actual changed files/components against the declared impact map; changes outside the declared surface = scope-creep finding (ties to principles-and-practices.md §2.5 Surgical changes). |
security/PRE_DEV_REVIEW.md |
Security — are the Required Controls (RC-N) and threat mitigations (S1..E10 from STRIDE) present in code? |
reports/TEST_REPORT.md |
Gate-6 PASS verdict (Step 2 trusts this instead of re-running the suite) + Coverage numbers + every OPEN-XXX debt from /test must be tagged CLOSED / DEFERRED-to-Pn / ESCALATED in this review — none may be silently dropped. |
db/schema-snapshot/ |
Schema-evidence freshness — if the diff contains a migration that changes the schema or a DB-resident object (proc/trigger/view/index) but the snapshot is untouched, the committed baseline is now stale: 🟡 finding (brownfield.md checklist). Also flag the reverse smell — a snapshot edited without a migration, which means someone changed the database by hand. |
.claude/rules/*.md |
Compliance Check table (see Output File §6). |
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.
- 6d ago First seen · 187 lines · 15 tokens per session scan A 955209614e47
review is a command published in the GitHub repository dinhnguyenngoc/spec-driven-claude-code (20 stars, last pushed 7d ago), licensed MIT. It adds 15 tokens to every session and 3,679 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.
Other commands, from other repositories
spec-kitty.implement
Spec-Driven Development for serious software developers. Spec Coding with with Claude, Cursor, Gemini, Codex. Kanban dashboard, git worktrees, auto-merge and more.
generate-design-md
Génère un DESIGN.md à la racine du projet à partir du template Claude Craft + analyse des sources UI existantes (Tailwind, tokens, CSS).
generate-hook
Génération Custom Hook React.
kiro-validate-design
Command "kiro-validate-design" from gotalab/cc-sdd, covering technical design validation, core task, execution steps, important constraints and tool guidance.
sdd-setup
Onboarding wizard — DocLanguage, Memory Bank, architecture snapshot, working agreements (quality gate, TDD working mode).
wayfind
Plan a chunk of work too big for one agent session as a shared decision map: map.md + typed decision tickets in the mega-goal folder, resolved one per session through the kit's own grill/prototype/research machinery, until nothing is left to decide. Then hand off to /kit:spec or a ROADMAP, never straight to execute.