role-reviewer

role-reviewer is a skill for Claude Code from BechsteinDigital/claude-shiploop. It costs 54 tokens per session (1,011 once invoked), scanned A, original, MIT.

A code-review role for checking one completed work package or a limited code change against its requirements.

In plain words
What is it for?
Use it to inspect a bounded diff, verify acceptance criteria and status claims, assess test quality, and report risks or caveats.
Why use it?
It focuses review on the intended change, its risks, tests, and completion claims instead of reopening the entire project.

Skill for Claude Code

Written for Claude Code: disallowed-tools in frontmatter. Also seen: model in frontmatter; reads .claude/ paths; mentions subagents.

Part of the claude-shiploop plugin — 8 skills shipped together

Good fit Use it to inspect a bounded diff, verify acceptance criteria and status claims, assess test quality, and report risks or caveats.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/bechsteindigital/claude-shiploop/role-reviewer
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 BechsteinDigital/claude-shiploop --skill role-reviewer
Clone the repo
git clone --depth 1 https://github.com/BechsteinDigital/claude-shiploop

Made for: Claude Code.

Or install claude-shiploop, the plugin that ships this one along with the rest of its 8 skills.

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 role-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/skills/bechsteindigital/claude-shiploop/role-reviewer/github.svg)](https://agentmods.dev/skills/bechsteindigital/claude-shiploop/role-reviewer)
Your own site
<a href="https://agentmods.dev/skills/bechsteindigital/claude-shiploop/role-reviewer"><img src="https://agentmods.dev/badge/skills/bechsteindigital/claude-shiploop/role-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.

agentmods 80×15 button for role-reviewer

Your own site · 80×15
<a href="https://agentmods.dev/skills/bechsteindigital/claude-shiploop/role-reviewer"><img src="https://agentmods.dev/badge/skills/bechsteindigital/claude-shiploop/role-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 54 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,011 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00054 $0.01011
Opus 5 $0.00027 $0.00505
Sonnet 5 $0.00011 $0.00202
Haiku 4.5 $0.00005 $0.00101

Measured 11d ago against content hash 1bc748bbaaad, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

role-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 11d 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.

role-reviewer/SKILL.md · 60 lines

How it starts

The opening of the file, as written. The whole thing — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.

REVIEWER Role (project-agnostic, silent)

Role

Checks the delta: exactly one package or bounded diff against its WORK card. No refactoring, no reimplementation, no whole-project review.

Required input

Invoked directly, $ARGUMENTS = <WORK-card> <base> <head> (e.g. WORK-042 main HEAD); in the loop these arrive embedded from the orchestrator.

  1. the package's WORK card (acceptance criteria, non-goals, claim limits, claim zone)
  2. compact diff scan: <skills-dir>/_shared/scripts/compact-diff-scan.sh <base> <head><skills-dir> is the installation location of these skills (project-local .claude/skills/, global ~/.claude/skills/, or the plugin root when installed via /plugin install); risk regex from project/PROFILE.md
  3. project/PROFILE.md — quality rules, architecture overview
  4. DEV output (TESTS/CAVEATS/ZONE)

Scan compactly first, then deepen only risky files. No full diff as default.

Review tiers

  • Full review (all mandatory checks below) for: production code, gate-relevant packages, risk-regex hits in the diff, or included status claims.
  • Light review for trivial packages (tests/docs only, small diff): zone check, acceptance check, targeted tests, compact claim audit — pattern spot-check omitted. When in doubt: full review.
  • Tests always targeted for zone and criteria — the full suite belongs to the orchestrator at merge, don't duplicate.

Mandatory checks

  1. Acceptance check: which diff parts prove which criterion? Unproven criteria are findings, not a pass.
  2. Zone check: changes outside the claim zone = scope-creep finding, regardless of the change's quality.
  3. Claim audit: for DONE, finished, complete, compliant in diff, docs, or handoff: proven by code? Proven by tests? Criteria fully covered? Caveats? Docs may never claim more than code + tests prove; substantial caveat → "partial" instead of "done"; upgrade without proof = blocker.
  4. Test quality: do the tests verify the claimed behavior or only the green path? Missing negative cases/edge conditions? Were old tests adjusted to fit?
  5. Architecture & rules: against project/PROFILE.md. Works but violates guardrails → finding.
  6. Pattern spot-check: if the diff touches concurrency, lifecycle/resource release, or module boundaries: read 2–3 neighboring implementations of the same pattern. Deviation from the majority pattern is a finding, even if the diff looks correct in isolation. Spot check, not a repo scan (→ role-auditor).

Read the full file on GitHub · 60 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.

  1. 11d ago First seen · 60 lines · 0 tokens per session scan A 1bc748bbaaad

Subscribe to this mod's changes

role-reviewer is a skill published in the GitHub repository BechsteinDigital/claude-shiploop (4 stars, last pushed 1mo ago), licensed MIT. It adds 54 tokens to every session and 1,011 once invoked, about $0.0003 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.

Related

Other skills, from other repositories

cleanup-audit

Audit codebase for dead code, unused exports, orphaned files, and stale manifests.

jmagly/aiwg · 21 tokens

link-check

Verify @file references in AIWG skills and agents against the linking contract — per-file or corpus-wide, with optional auto-fix.

jmagly/aiwg · 29 tokens

suede-code-review

Suede Labs AI findings-only code review with full context: changed files, callers, contracts, and deploy surface. Covers TypeScript, React, Next.js, database, Swift/iOS, OWASP, accessibility, SEO, observability, commit hygiene, and deploy risk, ranked P0-P3 with file:line evidence and a fix path. Use when asked to…

JasonColapietro/suede-creator-skills · 191 tokens

suede-code

Suede Labs AI combined code review and ship grade in one pass: findings with file:line evidence plus an A-F lane grade, Instant-F security triggers, OWASP checks, a deploy-safety gate, and fix briefs. Use when asked to review this, grade this, security-check this, is this safe to ship, or check this PR before merge …

JasonColapietro/suede-creator-skills · 167 tokens

suede-code-grader

Suede Labs AI blunt A-F ship grade for a code change across correctness, security and permissions, data and state, domain truth, UX and release behavior, tests and verification, and deploy readiness, with Instant-F triggers and evidence-based grade caps on auth, payment, migration, and public-API surfaces. Use when…

JasonColapietro/suede-creator-skills · 156 tokens

Systematic debugging

Use when you hit a bug, test failure, or unexpected behavior — find the root cause before changing code.

Kilbex/Vigla · 26 tokens