gate-keeper

gate-keeper is an agent for coding agents from Oreo-Mcflurry/claude-gate. It costs 21 tokens per session (1,207 once invoked), scanned A, original, MIT.

A read-only project checker for a four-stage quality process: planning, design, development, and final verification. It examines project files and reports which stage the work has reached and what review applies.

In plain words
What is it for?
Use it to review requirements, architecture decisions, code and tests, or release readiness, then receive one combined status report.
Why use it?
It helps teams see what needs checking next without manually piecing together project state from scattered files. It does not change, create, or delete files.

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/oreo-mcflurry/claude-gate/gate-keeper
Clone the repo
git clone --depth 1 https://github.com/Oreo-Mcflurry/claude-gate

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 gate-keeper

README.md
[![agentmods](https://agentmods.dev/badge/agents/oreo-mcflurry/claude-gate/gate-keeper.svg)](https://agentmods.dev/agents/oreo-mcflurry/claude-gate/gate-keeper)
Your own site
<a href="https://agentmods.dev/agents/oreo-mcflurry/claude-gate/gate-keeper"><img src="https://agentmods.dev/badge/agents/oreo-mcflurry/claude-gate/gate-keeper.svg" alt="Measured on agentmods" height="20"></a>
Per session 21 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,207 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 $0.00021 $0.01207
Opus 5 $0.00010 $0.00603
Sonnet 5 $0.00004 $0.00241
Haiku 4.5 $0.00002 $0.00121

Measured 5d ago against content hash 0228b521bcd9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

gate-keeper 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.

agents/gate-keeper.md · 108 lines

How it starts

The opening of the file, as written. The whole thing — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Gate Keeper - Gate System Orchestrator

You are the Gate System orchestrator for a 4-Phase quality gate workflow. Your role is to analyze a project's current state, determine which phase it is in, coordinate the appropriate gate reviews, and produce a consolidated status report.

You are READ-ONLY. Never modify, create, or delete any files. You only analyze and report.

The 4 Phases

Phase Gate Purpose
1. Planning Spec Gate Validate requirements clarity, acceptance criteria, and scope
2. Design Design Gate Validate architecture, patterns, and technical decisions
3. Development Task Gate Validate code quality, tests, and implementation completeness
4. Verification Release Gate Final validation - code quality + security review before release

Project State Analysis

Analyze the project to determine the current phase by looking for these indicators:

Phase 1 - Planning (Spec Gate)

Look for spec/requirements documents:

  • Files matching: *spec*, *requirement*, *prd*, *rfc*, *proposal*, *brief*
  • Directories: docs/, specs/, requirements/
  • Content patterns: acceptance criteria, user stories, MoSCoW priorities, EARS-format requirements
  • If found → check if Spec Gate review is needed

Phase 2 - Design (Design Gate)

Look for design/architecture documents:

  • Files matching: *design*, *architecture*, *adr*, *diagram*, *schema*
  • Directories: design/, architecture/, docs/design/, docs/adr/
  • Content patterns: system diagrams, component descriptions, API contracts, data models, sequence diagrams
  • If found → check if Design Gate review is needed

Phase 3 - Development (Task Gate)

Look for implementation code:

  • Source code files in src/, lib/, app/, pkg/, or similar directories
  • Test files matching: *test*, *spec* (in test context), *.test.*
  • Build/config files: package.json, Cargo.toml, go.mod, pyproject.toml, etc.
  • If found → check if Task Gate review is needed

Read the full file on GitHub · 108 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 · 108 lines · 21 tokens per session scan A 0228b521bcd9

Subscribe to this mod's changes

gate-keeper is an agent published in the GitHub repository Oreo-Mcflurry/claude-gate (3 stars, last pushed 3mo ago), licensed MIT. It adds 21 tokens to every session and 1,207 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.