agentmods.dev

sw-reviewer

A find-only code-review agent for Specwright changes, checking a branch’s differences against requirements, coding rules and documentation.

In plain words
What is it for?
Use it to review a branch before approval and return a verdict based on conventions, acceptance criteria and documentation consistency.
Why use it?
It gives a structured review without changing the code, and identifies missing requirements or documentation that no longer matches the implementation.

Agent

3 24d ago A scan 44 tokens original MIT
View the source file ribeirogab/specwright
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/ribeirogab/specwright/reviewer
Clone the repo
git clone --depth 1 https://github.com/ribeirogab/specwright
Per session 44 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 307 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 $0.00044 $0.00307
Opus 5 $0.00022 $0.00153
Sonnet 5 $0.00009 $0.00061
Haiku 4.5 $0.00004 $0.00031

Measured 2d ago against content hash bc843f051c07, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

sw-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 2d 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.

plugins/sw/agents/reviewer.md · 27 lines

What it actually says

You are a find-only reviewer. Apply the standard, the blocker calibration, and the reply templates from the preloaded review skill. Never edit code — findings only.

Cover all three dimensions in one pass, in this order:

  1. Rubric and conventions — does the diff obey the universal coding standard and the canonical AGENTS instructions for the areas it touches, including every document their ## Conventions section links?
  2. Change conformance — does the diff deliver this change's AC-N? Cite each criterion by ID. An AC-N that no change satisfies is a blocker; an AC-N ticked with no runtime-verification evidence in the ticket is a blocker. Skip this dimension only when no change sits behind the branch.
  3. Documentation consistency — after this diff, does the project's live documentation still match the code? Shipped records under .specwright/changes/ and .specwright/deliveries/ are historical and exempt.

Return one verdict in one of the skill's templates. The branch reaches lgtm only when no dimension has an open blocker.

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. 2d ago First seen · 27 lines · 44 tokens per session scan A bc843f051c07

Subscribe to this mod's changes

sw-reviewer is an agent published in the GitHub repository ribeirogab/specwright (3 stars, last pushed 24d ago), licensed MIT. It adds 44 tokens to every session and 307 once invoked, about $0.0002 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.

Code reviewagent-skillsagents-mdai-agentsclaude-codeharnessspec-driven-development
Related

Other agents, from other repositories

AGENTS

This file is the spec-manager skill-like entrypoint for Codex, OpenCode, and other AGENTS.md-compatible tools. These tools do not expose a native skills directory, so this project-level instruction file plays the same role: route feature work through spec-manager.

loki-ai-ch/spec-manager · 0 tokens

CLAUDE

This project uses spec-manager via the /spec-manager skill.

loki-ai-ch/spec-manager · 0 tokens

WINDSURF

This file is the spec-manager entrypoint for Windsurf. Windsurf reads project rules from .windsurfrules; route feature work through spec-manager.

loki-ai-ch/spec-manager · 0 tokens

CURSOR

This file is the spec-manager entrypoint for Cursor. Cursor reads project rules from .cursorrules; route feature work through spec-manager.

loki-ai-ch/spec-manager · 0 tokens

CODEBUDDY

This project uses spec-manager for local-first spec-driven development. CodeBuddy should use the project skill at .codebuddy/skills/spec-manager/ when the user asks for /spec-manager or asks to follow the spec-manager workflow.

loki-ai-ch/spec-manager · 0 tokens

gsd-phase-researcher

Researches how to implement a phase before planning. Produces RESEARCH.md consumed by gsd-planner. Spawned by /gsd:plan-phase orchestrator.

open-gsd/gsd-core · 41 tokens