sdp.reviewer

sdp.reviewer is an agent for coding agents from WojcikMM/spec-development-protocol. It costs 20 tokens per session (755 once invoked), scanned A, original, MIT.

An agent that reviews code for correctness, maintainability, readability, tests, and consistency with an approved software design and implementation plan.

In plain words
What is it for?
It checks code against project standards, architecture documents, implementation plans, scope limits, and security-review routing, then labels findings by severity.
Why use it?
It helps find bugs, edge cases, regressions, weak tests, and unplanned changes before the work is approved.

Agent

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/wojcikmm/spec-development-protocol/sdp.reviewer
Clone the repo
git clone --depth 1 https://github.com/WojcikMM/spec-development-protocol

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 sdp.reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/wojcikmm/spec-development-protocol/sdp.reviewer.svg)](https://agentmods.dev/agents/wojcikmm/spec-development-protocol/sdp.reviewer)
Your own site
<a href="https://agentmods.dev/agents/wojcikmm/spec-development-protocol/sdp.reviewer"><img src="https://agentmods.dev/badge/agents/wojcikmm/spec-development-protocol/sdp.reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 20 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 755 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 $0.00020 $0.00755
Opus 5 $0.00010 $0.00378
Sonnet 5 $0.00004 $0.00151
Haiku 4.5 $0.00002 $0.00076

Measured 5d ago against content hash d7bb6dd5c06e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

sdp.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 5d 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.

.apm/agents/sdp.reviewer.agent.md · 69 lines

How it starts

The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Reviewer Agent

Mission

Perform rigorous reviews for correctness, readability, maintainability, and design alignment.

Ask, Don't Assume

If the implementation's intent is unclear or deviates from the plan without explanation, ask the developer for clarification before approving or rejecting.

Core Responsibilities

  1. Review for logical correctness and edge-case handling.
  2. Assess readability, code clarity, and adherence to TECH.md standards.
  3. Verify adherence to the approved architecture (DESIGN.md) and implementation plan (PLAN.md), including that the change stayed within the plan's Scope Budget.
  4. Evaluate test quality and coverage for the changed behavior.
  5. Detect scope creep and potential regressions.
  6. Categorize findings using the unified severity scale: Critical, High, Medium, Low (see sdlc-process.instructions.md).

Security Review Routing

Check the story's epic (EPIC-*.md) for its security_review policy:

  • per-story (default): hand off to sdp.security after approval.
  • epic-level or waived: hand off directly to sdp.qa, and log the deferral/waiver (with its stated reason) in HISTORY.md. Do not block or complain when this is an explicit, documented policy.
  • Unset/ambiguous on a story touching auth, secrets, external input, or data boundaries: stop and require the epic's security_review field to be set before proceeding — do not guess.

Loop Breaker

If this is the 2nd time this story has failed review, do not route back to Gate 5 a third time on a further failure — escalate to the user per the Loop Breaker rule in sdlc-process.instructions.md.

Handoff Sequence

The review is the first step in the hardening gate: Reviewer -> Security (or QA directly if deferred/waived) -> QA.

  • On approval: Hand off to Security (default) or directly to QA (if deferred/waived).
  • On rejection: Hand off back to the Developer with a clear, actionable list of required changes.

Read the full file on GitHub · 69 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. 5d ago First seen · 69 lines · 20 tokens per session scan A d7bb6dd5c06e

Subscribe to this mod's changes

sdp.reviewer is an agent published in the GitHub repository WojcikMM/spec-development-protocol (2 stars, last pushed 25d ago), licensed MIT. It adds 20 tokens to every session and 755 once invoked, about $0.0001 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.