Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add pwdev-solucoes/pwdev-claude-marketplace/plugin install pwdev-codeWrote 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/pwdev-solucoes/pwdev-claude-marketplace/review)<a href="https://agentmods.dev/commands/pwdev-solucoes/pwdev-claude-marketplace/review"><img src="https://agentmods.dev/badge/commands/pwdev-solucoes/pwdev-claude-marketplace/review/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.
<a href="https://agentmods.dev/commands/pwdev-solucoes/pwdev-claude-marketplace/review"><img src="https://agentmods.dev/badge/commands/pwdev-solucoes/pwdev-claude-marketplace/review.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00024 | $0.01928 |
| Opus 5 | $0.00012 | $0.00964 |
| Sonnet 5 | $0.00005 | $0.00386 |
| Haiku 4.5 | $0.00002 | $0.00193 |
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 10d 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 — 184 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/pwdev-code:review — Code Review + QA Audit
Role (orchestrator — the subagents review; you consolidate)
Input
$ARGUMENTS: optional scope filter
| Argument | What it does |
|---|---|
| (empty) | Review all changes since last commit (or staged changes) |
[file paths] |
Review specific files |
--code-only |
Run only code review (skip QA) |
--tests-only |
Run only QA test audit (skip code review) |
--diff HEAD~N |
Review last N commits |
Entry Gate
git diff --name-only HEAD~1..HEAD 2>/dev/null || git diff --staged --name-only 2>/dev/null
If no changes found:
⚠️ No changes detected to review.
Specify files: /pwdev-code:review src/UserService.ts
Or a range: /pwdev-code:review --diff HEAD~3
Flow
Re-review scope rule: when re-running after execute --fix or
/pwdev-code:simplify (state.md shows review_gate: STALE), scope = the
fix/refactor commits only (--diff), never the whole phase again.
STEP 0 — Language
Follow ${CLAUDE_PLUGIN_ROOT}/references/language.md (resolve lang from
.planning/config.json; ask only if unset).
STEP 1 — Determine Scope
if [ -n "$ARGUMENTS" ]; then
FILES="$ARGUMENTS"
else
FILES=$(git diff --name-only HEAD~1..HEAD 2>/dev/null || git diff --staged --name-only)
fi
echo "$FILES"
STEP 2 — Gather Spawn Inputs
Read (for the prompts only — do not analyze yourself):
.planning/phases/{active-phase-slug}/spec.md sections 1, 2, 5, 7, 8;
paths of execution/*-summary.md; active skills list; RELEVANT MEMORY block
per ${CLAUDE_PLUGIN_ROOT}/references/memory.md (conventions first) — add
it to both spawn prompts.
STEP 3 — Spawn Subagents (REAL parallelism)
Default: issue BOTH Task tool calls in a SINGLE message so they run in
parallel. --code-only → only code-reviewer; --tests-only → only qa.
Resolve each model per ${CLAUDE_PLUGIN_ROOT}/references/model-profiles.md.
subagent_type: "pwdev-code:code-reviewer"— prompt from the code-reviewer template in${CLAUDE_PLUGIN_ROOT}/references/spawn-contracts.md(scope = file list/diff range, spec §1/5/7, conventions pointer, skills,LANGUAGE: {lang}). Writes:review/code-review.md.subagent_type: "pwdev-code:qa"— prompt from the qa template (spec §2/5/8, summary paths, skills,LANGUAGE: {lang}). Writes:review/qa-report.md.
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.
- 10d ago First seen · 184 lines · 24 tokens per session scan A 0c6adda2032d
review is a command published in the GitHub repository pwdev-solucoes/pwdev-claude-marketplace (2 stars, last pushed 3d ago), licensed Apache-2.0. It adds 24 tokens to every session and 1,928 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.
Other commands, from other repositories
test
Run the repository's actual test suite: every ecosystem's canonical runner — NOT run is never green.
ia-verify
Run pre-PR verification chain -- build, types, lint, tests, security scan, diff review.
audio-pass
Functional audio review for implementation, mix coverage, clarity, and player feedback.
quality-check-command
This command performs comprehensive code quality checks. Use it before commits or when implementation is complete.
auditar-refactor
Invoca refactor-safety-auditor — gate canônico antes de qualquer refactor. Coleta evidências (linhas, contrato externo, coverage, mutation) e retorna veredito GO/BLOCK/WARN/GO-OVERRIDE.
gentle-sdd-apply
Implement SDD tasks — writes code following specs and design.