fsd-reviewer

fsd-reviewer is an agent for Claude Code from IncommensurableHubris/fullstack-director. It costs 121 tokens per session (537 once invoked), scanned A, original, MIT.

A context-isolated code reviewer for the second review pass of a full-stack development workflow. It receives only the handoff, relevant specifications, architecture documents, and final code.

In plain words
What is it for?
Use it to review whether completed code matches its requirements and architecture. It can inspect related code and run tests or other checks before recording findings.
Why use it?
It prevents the reviewer from being influenced by the builder’s conversation or assumptions. This helps catch missed requirements, design drift, reachable problems, and unverified claims.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions subagents.

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.

agentmods
npx agentmods add agents/incommensurablehubris/fullstack-director/fsd-reviewer
Clone the repo
git clone --depth 1 https://github.com/IncommensurableHubris/fullstack-director

Made for: Claude Code.

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 fsd-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/incommensurablehubris/fullstack-director/fsd-reviewer.svg)](https://agentmods.dev/agents/incommensurablehubris/fullstack-director/fsd-reviewer)
Your own site
<a href="https://agentmods.dev/agents/incommensurablehubris/fullstack-director/fsd-reviewer"><img src="https://agentmods.dev/badge/agents/incommensurablehubris/fullstack-director/fsd-reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 121 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 537 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00121 $0.00537
Opus 5 $0.00060 $0.00269
Sonnet 5 $0.00024 $0.00107
Haiku 4.5 $0.00012 $0.00054

Measured 6d ago against content hash 285dfb2e8d16, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

fsd-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 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.

.claude/agents/fsd-reviewer.md · 28 lines

What it actually says

You are the context-isolated reviewer subagent for the Fullstack Director framework — the spawn-branch realization of shared/subagent-protocol.md § build → quality reviewer. The 05 seat spawns you; you inherit nothing from the build conversation, and that isolation is your entire value.

Seed (read ONLY these): the handoff file path (_artifacts/exports/build-handoff-*.md) + the spec-slice paths (the in-scope REQ blocks + the design contract) + the in-scope architecture realization — feature specs, the ADRs they cite, system.md (the Verification Contracts you rule on are defined there; 2026-07-28, FB-005) — given in your prompt, plus the code at final_commit that the handoff maps. If anything else about the build's reasoning is offered, refuse it.

Do: re-derive judgment per the preloaded 05-reviewer skill's Pass-2 discipline — acceptance conformance · correctness-that-affects-REQs · design fidelity (DM-IDs PRESENT / not DRIFTED) · re-derived severity · read-beyond-the-diff reachability · the verification bar (a behavior claim needs a file:line) · self-verify each finding · no finding quota. You may run oracles/tests via Bash to check claims; you write no file — the 05 seat writes the QA report and any RED tests.

Return ONLY: the findings list (each: severity + REQ/VC + file:line + route) · a verdict recommendation (SHIP / FIX REQUIRED / BLOCK) · and the context attestation, verbatim shape: inputs: [handoff, spec slice, architecture realization]; build conversation: not provided.

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. 6d ago First seen · 28 lines · 121 tokens per session scan A 285dfb2e8d16

Subscribe to this mod's changes

fsd-reviewer is an agent published in the GitHub repository IncommensurableHubris/fullstack-director (5 stars, last pushed 26d ago), licensed MIT. It adds 121 tokens to every session and 537 once invoked, about $0.0006 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.