code-review-policy

code-review-policy is a skill for Claude Code from babyworm/rtl-agent-team. It costs 18 tokens per session (427 once invoked), scanned A, original, MIT.

An internal reference that defines how code reviews classify findings from blockers to minor issues. It covers RTL correctness, testbench quality, verification coverage, and risks affecting manufactured hardware.

In plain words
What is it for?
It is for evaluating hardware code reviews, documenting serious findings, and deciding whether a phase can pass its quality gate.
Why use it?
It gives reviewers consistent severity levels and evidence requirements, including when work must fail or be escalated.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter.

Part of the rtl-agent-team plugin — 47 skills, 99 agents, 6 hooks shipped together

Good fit It is for evaluating hardware code reviews, documenting serious findings, and deciding whether a phase can pass its quality gate.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/babyworm/rtl-agent-team/code-review-policy
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.

Any agent
npx skills add babyworm/rtl-agent-team --skill code-review-policy
Clone the repo
git clone --depth 1 https://github.com/babyworm/rtl-agent-team

Made for: Claude Code.

Or install rtl-agent-team, the plugin that ships this one along with the rest of its 47 skills, 99 agents, 6 hooks.

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 code-review-policy

README.md
[![agentmods](https://agentmods.dev/badge/skills/babyworm/rtl-agent-team/code-review-policy.svg)](https://agentmods.dev/skills/babyworm/rtl-agent-team/code-review-policy)
Your own site
<a href="https://agentmods.dev/skills/babyworm/rtl-agent-team/code-review-policy"><img src="https://agentmods.dev/badge/skills/babyworm/rtl-agent-team/code-review-policy.svg" alt="Measured on agentmods" height="20"></a>
Per session 18 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 427 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00018 $0.00427
Opus 5 $0.00009 $0.00214
Sonnet 5 $0.00004 $0.00085
Haiku 4.5 $0.00002 $0.00043

Measured 4d ago against content hash 7fcf8895ce12, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

code-review-policy 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 4d 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.

skills/code-review-policy/SKILL.md · 57 lines

What it actually says

Code Review Policy

Scope

  • RTL logic correctness and spec/uarch compliance
  • Testbench quality and checker/scoreboard adequacy
  • Verification completeness (coverage + traceability)
  • Silicon risk indicators (constraints/CDC/synthesis/timing impacts)

Severity

  • S0 Blocker: data corruption, protocol/safety breakage, hard spec violation
  • S1 Critical: high silicon risk, functional failure likely under valid stimulus
  • S2 Major: maintainability/test-quality issues with medium defect risk
  • S3 Minor: style/readability/non-blocking improvements

Pass/Fail Gate

  • FAIL: any unresolved S0 or S1
  • CONDITIONAL: only S2 findings remain and have approved remediation plan
  • PASS: only S3 or no findings

Escalation

  • Any S0: immediate stop, escalate to orchestrator/user with fix-first recommendation
  • Repeated S1 on same module after 2 fix loops: escalate to architecture owner
  • Missing evidence for S0/S1: finding is invalid until evidence attached

Evidence Rules

  • Every S0/S1 finding must include reproducible evidence:
    • file and line
    • failing command/log snippet
    • expected vs actual behavior
  • Prefer replay artifacts (*_latest.sh, wave/report paths) over prose-only claims

Output Format

Use the following report skeleton:

# Code Review Report
- Scope: module|block|top
- Verdict: PASS | CONDITIONAL | FAIL

## Findings
| ID | Severity | File:Line | Summary | Evidence |
|---|---|---|---|---|

## Required Actions
| Priority | Owner | Action | Recheck |
|---|---|---|---|

## Escalations
- [if any]
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. 4d ago First seen · 57 lines · 18 tokens per session scan A 7fcf8895ce12

Subscribe to this mod's changes

code-review-policy is a skill published in the GitHub repository babyworm/rtl-agent-team (51 stars, last pushed 14d ago), licensed MIT. It adds 18 tokens to every session and 427 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 2026-09-03.

Related

Other skills, from other repositories

qa-review

QA review for code changes — test coverage analysis, edge case identification, test plan generation, regression detection, test health tracking over time.

suyoumo/ClawProBench · 30 tokens

flutter-mcp-boundary-audit

Generic contract/schema boundary audit across authoring, discovery, validation, and execute—detecting split-brain between listings and invoke paths, gateway divergence, and permissive placeholders. Use when changing tool registration, RPC/plugin registries, dynamic tools, MCP or WebMCP surfaces, CLI exec aliases…

Arenukvern/mcp_flutter · 92 tokens

readable-verilog-generator

Use when creating, writing, reviewing, annotating, repairing, refactoring, or validating readable Verilog RTL, including synthesizable Verilog-2001 .v files, existing-RTL analysis, semantic comment annotation, testbench scaffold planning, ASIC-quality review, local or remote Vivado/xsim validation, evidence-backed…

Eriemon/verilog-generator · 77 tokens

fresh-eyes-loop

A repeatable quality-review process using two independent agents: one reviews and verifies, while the other fixes issues. P0 and P1 mean the highest-severity problem levels.

KongFangXun/sofagent · 58 tokens

aster-review-ci

Run aster code reviews non-interactively in CI, GitHub Actions, or from another agent. Covers aster review --pr, --json, --stream, --comment, diff-from-stdin, token handling, and filtering findings. Use when wiring aster into a pipeline, posting PR comments, or parsing review output programmatically.

Zfinix/aster · 75 tokens

rtl-review

Audit RTL code for lint violations, synthesis hazards, coding-style compliance, and readability. Use when the user says "review this Verilog", "check my RTL", "lint this module", "is this code synthesizable", or shares an HDL file and asks for feedback before simulation or tape-in.

vibeic/vibe-ic · 63 tokens