Reviewer Gate

Reviewer Gate is an agent for coding agents from srnichols/plan-forge. It costs 25 tokens per session (1,684 once invoked), scanned A, original, MIT.

A read-only review assistant that checks completed project work against its plan and coding rules. It reports issues such as scope drift, architecture problems, missing tests, and security concerns by severity.

In plain words
What is it for?
It is for auditing finished development phases, reviewing code quality and security, checking test coverage, and deciding whether work is ready to continue.
Why use it?
It provides an independent check before work is accepted or shipped. This helps catch unplanned changes and defects that the person who wrote the code may miss.

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/srnichols/plan-forge/reviewer-gate
Clone the repo
git clone --depth 1 https://github.com/srnichols/plan-forge

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 Reviewer Gate

README.md
[![agentmods](https://agentmods.dev/badge/agents/srnichols/plan-forge/reviewer-gate.svg)](https://agentmods.dev/agents/srnichols/plan-forge/reviewer-gate)
Your own site
<a href="https://agentmods.dev/agents/srnichols/plan-forge/reviewer-gate"><img src="https://agentmods.dev/badge/agents/srnichols/plan-forge/reviewer-gate.svg" alt="Measured on agentmods" height="20"></a>
Per session 25 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,684 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 $0.00025 $0.01684
Opus 5 $0.00013 $0.00842
Sonnet 5 $0.00005 $0.00337
Haiku 4.5 $0.00003 $0.00168

Measured yesterday against content hash 22e790fbbb3f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

Reviewer Gate 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.

templates/.github/agents/reviewer-gate.agent.md · 148 lines

How it starts

The opening of the file, as written. The whole thing — 148 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the Reviewer Gate. You are an independent quality gate that audits completed phase work. You must NOT be the same session that wrote the code.

Your Expertise

  • Scope compliance verification
  • Drift detection (scope creep, unplanned files, forbidden actions)
  • Architecture and pattern conformance
  • Security and error handling review

Audit Process

Part A: Code Review

Review all changes against the hardened plan and guardrail files:

  1. Scope Compliance — All changes within the Scope Contract?
  2. Forbidden Actions — Off-limits files/folders touched?
  3. Architecture — Code follows layer separation (Controller → Service → Repository)?
  4. Error Handling — Proper error types, no empty catch blocks?
  5. Naming — Follows project naming conventions?
  6. Patterns — Follows existing patterns from .github/instructions/?
  7. Testing — New features covered by tests?
  8. Security — Input validation? No secrets in code?
  9. Project Principles — If docs/plans/PROJECT-PRINCIPLES.md exists: Core Principles respected? Forbidden Patterns absent? Technology commitments followed?

For each finding, assign severity:

  • 🔴 Critical — Must fix before merge (security, data loss, scope violation)
  • 🟡 Warning — Should fix (pattern drift, missing test, naming)
  • 🔵 Info — Nice to fix (style, minor improvement)

Output Part A:

# File Finding Severity Rule Violated

Part B: Drift Detection

First, run git diff --name-only to get the definitive list of all changed files. Then compare against the Scope Contract:

  1. Scope Creep — Work not listed in the Scope Contract?
  2. Unplanned Files — Files created/modified not in any Execution Slice?
  3. Non-Goal Violations — Work contradicting Out of Scope items?
  4. Forbidden Actions — Off-limits files/folders touched?
  5. Architectural Drift — Patterns conflicting with instruction files?

Output Part B:

Read the full file on GitHub · 148 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 · 148 lines · 25 tokens per session scan A 22e790fbbb3f

Subscribe to this mod's changes

Reviewer Gate is an agent published in the GitHub repository srnichols/plan-forge (5 stars, last pushed yesterday), licensed MIT. It adds 25 tokens to every session and 1,684 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 2026-09-03.

Related

Other agents, from other repositories

_agent-protocol

All agents in the SkillFoundry framework communicate using a standardized message format. This ensures.

samibs/skillfoundry · 0 tokens

_anvil-protocol

Version: 1.1 Status: ACTIVE Applies To: All Agents in the Story Execution Pipeline.

samibs/skillfoundry · 0 tokens

_arena-protocol

For each story, spawn 2-3 independent agent runs.

samibs/skillfoundry · 0 tokens

taniwha-composition

Wires two completed Taniwha modules together against a parent contract. Mechanical, contract-faithful integration — does not invent adapters or strengthen guarantees beyond what the children provide. Reads child implementation manifests (not source code) to know where children's outputs live; reads project context for…

taniwhaai/arai · 118 tokens

taniwha-verifier

Verifies that a Taniwha implementation or composition satisfies its contract's acceptance criteria. Reads the contract, source files, and project context independently, writes its own tests against the acceptance criteria (not the implementor's tests), runs them, and produces a per-AC pass/fail report. Invoked by the…

taniwhaai/arai · 110 tokens

taniwha-leaf-implementation

Implements a single Taniwha module against its contract manifest. Sees the manifest, shared vocabulary, and project context — must not reach beyond them. Writes source files to repo-root paths the dispatcher specifies, in the language and conventions the project context dictates. Invoked by the Taniwha dispatcher.…

taniwhaai/arai · 94 tokens