A fresh-context code reviewer that checks a sprint's implementation against its requirements and design contract. A sprint is a defined piece of planned development work.

Use it to verify completed sprint slices, check tests against expected outcomes, and produce a SHIP, FIX REQUIRED, or BLOCK decision with a severity summary.

It provides an independent review without carrying over assumptions from the build conversation. Its verdict helps determine whether the work can ship or needs fixes.

05-reviewer — Skill for Claude Code and Codex by IncommensurableHubris

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 IncommensurableHubris/fullstack-director --skill 05-reviewer

Clone the repo

git clone --depth 1 https://github.com/IncommensurableHubris/fullstack-director

Made for: Claude Code, Codex.

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/skills/incommensurablehubris/fullstack-director/05-reviewer/github.svg)](https://agentmods.dev/skills/incommensurablehubris/fullstack-director/05-reviewer)

Your own site

<a href="https://agentmods.dev/skills/incommensurablehubris/fullstack-director/05-reviewer"><img src="https://agentmods.dev/badge/skills/incommensurablehubris/fullstack-director/05-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/skills/incommensurablehubris/fullstack-director/05-reviewer"><img src="https://agentmods.dev/badge/skills/incommensurablehubris/fullstack-director/05-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 267 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 4,065 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 1 finding. 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	$0.00267	$0.04065
Opus 5	$0.00133	$0.02032
Sonnet 5	$0.00053	$0.00813
Haiku 4.5	$0.00027	$0.00407

Measured 9d ago against content hash 395c8c7e030b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

05-reviewer scanned grade A with 1 finding 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.

The scan reads SKILL.md. This mod also ships 10 executable files (evals/build_fixture.py, evals/check_review.py, evals/fixtures/clean/src/digest.js, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

(write/run a durable test → EXECUTED) → Tier 2/3 (Playwright / browser → OBSERVED) → Tier 4 (CLI/curl → OBSERVED).

.agents/skills/05-reviewer/SKILL.md · 159 lines

How it starts

The opening of the file, as written. The whole thing — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.

05 · Reviewer — verify

Two modes. 05-reviewer sprint N verifies one sprint's build; 05-reviewer full is the pre-release review across all shipped sprints. The context-isolated reviewer: spawned from a fresh session, seeded only with 04's build-handoff (_artifacts/exports/build-handoff-sprint-NN.md) + the spec-slice paths — never the build conversation — it verifies the realization against the spine's outcome-acceptance Gherkin + the 02 design contract and emits a SHIP / FIX REQUIRED / BLOCK verdict + a machine-readable tally + a context attestation. You are 03's sibling in the subagent tier and 04's consumer. Your graded value is not "reviews code" (a strong reviewer does that too) — it is the isolated, honest, false-positive-controlled verdict that can gate a ship.

Operating principle — verify in isolation, re-derive judgment, never fix

Seed + isolate. Read only the handoff + the spec-slice paths (the in-scope REQ blocks' outcome-Gherkin + the design contract). Isolation is real only because the spawner is fresh (shared/subagent-protocol.md). The semantic judgment (Pass 2) runs in a spawned fresh-context reviewer subagent (the 03 dual-pass pattern), which returns findings + verdict + the attestation.
Re-establish evidence, then re-derive judgment. Deterministic Pass 1 (re-run the oracles, coverage arithmetic, oracle-hash + spec-slice-hash + anti-tautology litmus) precedes the semantic Pass 2 (acceptance conformance · correctness-that-affects-REQs · design fidelity). Cheap structural gate before expensive judgment. Re-derive severity centrally; trust nothing the builder merely asserted.
Read-only, honest escalator. Write only the QA report + attestation + verification tests (incl. a reproducing RED test for each testable FIX REQUIRED finding, which 04 makes green). Never edit implementation. Build-time drift is surfaced and routed (three-way), never silently patched; append no amendment-log.json row (05 escalates, like 04).

Read the full file on GitHub · 159 lines

Files

What ships with it

37 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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 · 159 lines · 267 tokens per session scan A 395c8c7e030b

Subscribe to this mod's changes

05-reviewer is a skill published in the GitHub repository IncommensurableHubris/fullstack-director (5 stars, last pushed 29d ago), licensed MIT. It adds 267 tokens to every session and 4,065 once invoked, about $0.0013 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Claude Code Code review agent-skills ai-agents sdlc spec-driven-development

receiving-code-review

Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation.

obra/superpowers · 38 tokens

requesting-code-review

Use when completing tasks, implementing major features, or before merging to verify work meets requirements.

obra/superpowers · 22 tokens

gsd-ns-review

Route to the appropriate quality / review skill based on the user's intent. gsd-code-review-fix was absorbed by gsd-code-review --fix in #2790.

open-gsd/gsd-core · 16 tokens

spec-kitty-mission-review

Review a fully merged Spec Kitty mission post-merge (all WPs done/approved) to verify spec→code fidelity, FR coverage, drift, risks, and security. Triggers: "review the merged mission", "post-merge mission review", "verify the completed mission", "audit the mission implementation", "mission-level acceptance review"…

Priivacy-ai/spec-kitty · 155 tokens

spec-kitty-runtime-review

Review runtime-owned outputs using the Spec Kitty review workflow surface, then direct approval or rejection with structured feedback. Triggers: "review this work package", "check runtime output", "approve this step", "review WP", "is this WP ready to approve", "check this implementation". Does NOT handle: setup-only…

Priivacy-ai/spec-kitty · 85 tokens

best-practices

Apply modern web development best practices for security, compatibility, and code quality. Use when asked to "apply best practices", "security audit", "modernize code", "code quality review", or "check for vulnerabilities".

open-gsd/gsd-pi · 49 tokens

05-reviewer