requirements-reviewer

requirements-reviewer is an agent for Claude Code from cahenesy/throughline. It costs 80 tokens per session (1,541 once invoked), scanned A, original, MIT.

An independent review of changes to a product requirements document (PRD), which describes what a software product should do, before the PRD change is submitted. It checks requirement quality and compares the changes with the rest of the document.

In plain words
What is it for?
Use it to review new, changed, or removed requirements and assess their differences against the full PRD after the automated lint check.
Why use it?
It can catch contradictions, duplicates, unclear wording, terminology drift, and incorrectly recorded exceptions before implementation begins.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the throughline plugin — 7 skills, 5 agents, 2 hooks shipped together

Good fit Use it to review new, changed, or removed requirements and assess their differences against the full PRD after the automated lint check.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/cahenesy/throughline/requirements-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.

Clone the repo
git clone --depth 1 https://github.com/cahenesy/throughline

Made for: Claude Code.

Or install throughline, the plugin that ships this one along with the rest of its 7 skills, 5 agents, 2 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 requirements-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/cahenesy/throughline/requirements-reviewer/github.svg)](https://agentmods.dev/agents/cahenesy/throughline/requirements-reviewer)
Your own site
<a href="https://agentmods.dev/agents/cahenesy/throughline/requirements-reviewer"><img src="https://agentmods.dev/badge/agents/cahenesy/throughline/requirements-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 requirements-reviewer

Your own site · 80×15
<a href="https://agentmods.dev/agents/cahenesy/throughline/requirements-reviewer"><img src="https://agentmods.dev/badge/agents/cahenesy/throughline/requirements-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 80 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,541 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 $0.00080 $0.01541
Opus 5.5 $0.00032 $0.00616
Sonnet 5.5 $0.00016 $0.00308
Haiku 4.5 $0.00008 $0.00154

Measured yesterday against content hash 3a65d070c48f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

requirements-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 yesterday.

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.

agents/requirements-reviewer.md · 111 lines

How it starts

The opening of the file, as written. The whole thing — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a senior requirements engineer doing an INDEPENDENT review of a PRD change. You did not author it. You run in a fresh context that is not the author's session; that fresh context is the independence. You may be on the same model as the author. Do not spawn children.

Citations such as (FR-55) or (ADR 0005) in this prompt refer to the plugin's own design records, not to this repository's PRD or ADRs. Never look them up in the repository under review, and never cite them in a finding.

Your review is decision support for the human merge, not a quality guarantee. Spend your judgment where a model is needed: the mechanical pre-pass (prd-lint) has already run and was clean of blocking findings.

Inputs (from the dispatch prompt)

  • the repo root and the PRD path (docs/PRD.md);
  • the prd-lint: base <ref> line and any degrade line (base is HEAD …, no base …, base unparseable …); with a degrade line, apply judgement about which requirements are really new;
  • the delta lines (new<TAB><id>, changed<TAB><id>, removed<TAB><id>). When the dispatch gives no delta lines (the pre-pass was unavailable), derive the delta yourself from git diff <base> -- docs/PRD.md, or treat the whole PRD as new when there is no base;
  • the prd-lint vague.term info lines;
  • the report-file path.

Rules

  1. Scope. Check only the new and changed ids, one by one. Never re-litigate earlier requirements. Read the whole PRD for the set-level checks. A removed id is in scope only as a possible lost requirement (for example a rename that dropped content).
  2. Per-requirement checks. For each delta requirement, check that it is:
    • necessary: it traces to a stated user goal or problem;
    • unambiguous: there is exactly one reasonable reading;
    • complete: no missing actor, trigger or outcome;
    • singular: one need per requirement;
    • feasible: no conflict with the stated constraints;
    • verifiable: the — Acceptance: clause names an observable surface (what a user or program would see), never "a test exists" (FR-24);
    • conforms to the template: **<ID>-<n> <title>.** <text> — Acceptance: … under ## Requirements.
  3. Set-level checks of the delta against the whole PRD:
    • contradiction with an existing requirement, constraint or non-goal;
    • duplication of an existing requirement;
    • terminology drift, where the same concept is named differently.
  4. Readers' perspectives. Read the delta as the product owner, an implementer, a tester and a stakeholder. Report any finding that only one of them would raise.
  5. Rubric. Grade the PRD's ## Evaluation rubric rows (FR-77) as High-quality, Acceptable or Failing, citing each row's criterion. A Failing grade on any row is a BLOCK.
  6. Findings. Each finding is one line in exactly the shared format:

Read the full file on GitHub · 111 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. yesterday First seen · 111 lines · 80 tokens per session scan A 3a65d070c48f

Subscribe to this mod's changes

requirements-reviewer is an agent published in the GitHub repository cahenesy/throughline (3 stars, last pushed 2d ago), licensed MIT. It adds 80 tokens to every session and 1,541 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-10-16.

Related

Other agents, from other repositories

qa-tester

The QA Tester of the aSPARK team. Use in the Review phase (/demo-day) to test the running application hands-on in a real browser: verify every acceptance criterion from the spec, explore beyond the happy path, check console and network, and file reproducible bugs. Requires a browser integration (Claude in Chrome…

a-lottes/aSPARK · 79 tokens

product-owner

The Product Owner of the aSPARK team. Use in the Specify phase (/story-time) when a product idea or feature request must be challenged and turned into a spec with user stories and testable acceptance criteria. Also use when an existing spec needs re-prioritization or scope decisions, or in /next-steps to propose the…

a-lottes/aSPARK · 79 tokens

release-manager

The Release Manager of the aSPARK team. Use in the Keep phase (/go-live) to take a review- and QA-approved increment to release: fresh pre-flight checks, user-facing changelog, version tag, PR or deploy, post-release smoke check, and recording the cycle's learnings.

a-lottes/aSPARK · 64 tokens

reviewer

The Reviewer of the aSPARK team. Use in the Review phase (/peer-review) to audit the diff produced by /increment with a staff-engineer eye: plan conformance, correctness, edge cases, error handling, security and test quality. Writes the review report and may fix obvious low-risk issues directly.

a-lottes/aSPARK · 66 tokens

engineering-manager

The Engineering Manager of the aSPARK team. Use in the Plan phase (/sprint-plan) to turn an approved spec into a technical plan: architecture decision with rejected alternatives, ordered task breakdown, test strategy and risks. Also use when a plan must be revised after review or QA findings.

a-lottes/aSPARK · 62 tokens

designer

The Designer of the aSPARK team. Use in the Specify phase (/look-and-feel) to design-check a spec before planning starts, or later to critique an implemented UI (from screenshots or markup provided by the caller). Detects bad design: usability heuristics violations, inconsistency, accessibility problems.

a-lottes/aSPARK · 64 tokens