quality-gate-keeper

quality-gate-keeper is an agent for Claude Code from takahirom/takahirom-claude-code-marketplace. It costs 19 tokens per session (1,174 once invoked), scanned A, original, Apache-2.0.

A code-quality review step that examines the files changed in the current work and checks their tests, complexity, and unnecessary code.

In plain words
What is it for?
Use it after editing code and before committing, focusing on changed files and the relevant tests.
Why use it?
It catches weak tests, over-complicated changes, and avoidable clutter before code is committed.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: names the TodoWrite tool.

Part of the claude-code-quality-gate plugin — 1 agent, 2 hooks shipped together

Good fit Use it after editing code and before committing, focusing on changed files and the relevant tests.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/takahirom/takahirom-claude-code-marketplace/quality-gate-keeper
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/takahirom/takahirom-claude-code-marketplace

Made for: Claude Code.

Or install claude-code-quality-gate, the plugin that ships this one along with the rest of its 1 agent, 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 quality-gate-keeper

README.md
[![agentmods](https://agentmods.dev/badge/agents/takahirom/takahirom-claude-code-marketplace/quality-gate-keeper/github.svg)](https://agentmods.dev/agents/takahirom/takahirom-claude-code-marketplace/quality-gate-keeper)
Your own site
<a href="https://agentmods.dev/agents/takahirom/takahirom-claude-code-marketplace/quality-gate-keeper"><img src="https://agentmods.dev/badge/agents/takahirom/takahirom-claude-code-marketplace/quality-gate-keeper/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 quality-gate-keeper

Your own site · 80×15
<a href="https://agentmods.dev/agents/takahirom/takahirom-claude-code-marketplace/quality-gate-keeper"><img src="https://agentmods.dev/badge/agents/takahirom/takahirom-claude-code-marketplace/quality-gate-keeper.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 19 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,174 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 $0.00019 $0.01174
Opus 5 $0.00010 $0.00587
Sonnet 5 $0.00004 $0.00235
Haiku 4.5 $0.00002 $0.00117

Measured 11d ago against content hash d86ed17d0f70, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

quality-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 11d 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/claude-code-quality-gate/agents/quality-gate-keeper.md · 115 lines

How it starts

The opening of the file, as written. The whole thing — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a quality gate keeper. Your role is to:

Core Responsibilities

  1. Quality Gate Enforcement: Ensure code meets quality standards
  2. Test Quality: Detect missing assertions and test shortcuts
  3. Complexity Check: Identify unnecessary complexity and over-engineering
  4. Less is More: Remove redundant code, logs, comments, and conditions

Quality Gate Process

  1. Focus ONLY on current session changes - do NOT analyze entire codebase
  2. Identify actual changes made - diff against the main branch, not just the working tree, so committed-but-unmerged work is reviewed too:
    BASE=$(git merge-base HEAD main 2>/dev/null || git merge-base HEAD origin/main 2>/dev/null)
    git diff "$BASE"                          # tracked changes since branching from main
    git ls-files --others --exclude-standard  # new untracked files
    
  3. Check only modified files - ignore unchanged existing code
  4. Run ONLY relevant tests - not the entire test suite:
    • Tests for modified files only
    • Tests in the same directory/module
    • Use test patterns/filters when available
  5. Generate focused report - only issues in changed files

CRITICAL: Only analyze files that were actually modified in this session. Do NOT suggest changes to files that weren't touched.

Mode Selection (Automatic)

The mode is determined by test execution results:

  • Tests PASS ✅: Enforce all quality standards including debug code removal
  • Tests FAIL ❌: Focus on fixing tests, allow debug code temporarily
  • No Tests ⚠️: Require tests to be written first

Key Checks

Always Check (Both Modes):

  • Anti-cheat patterns:
    • Direct method calls instead of proper integration testing
    • Deleted tests to make them "pass"
    • Fake assertions or misleading output messages
    • Tests that bypass actual functionality testing
    • Changes made without running tests to verify they work
    • Assertions with incorrect expected values that don't match specification
    • Tests that appear to pass but actually test the wrong behavior
  • Test Quality: Missing assertions, debug output without expects
  • Test Execution: Verify tests were actually run after changes

Read the full file on GitHub · 115 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. 11d ago First seen · 115 lines · 19 tokens per session scan A d86ed17d0f70

Subscribe to this mod's changes

quality-gate-keeper is an agent published in the GitHub repository takahirom/takahirom-claude-code-marketplace (9 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 19 tokens to every session and 1,174 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.

Related

Other agents, from other repositories

cpp-reviewer

Expert C++ code reviewer specializing in memory safety, modern C++ idioms, concurrency, and performance. Use for all C++ code changes. MUST BE USED for C++ projects.

affaan-m/ECC · 41 tokens

reviewer

Read-only reviewer for an SDD implementation — checks that the change satisfies the acceptance criteria it claims (stage 1) and meets quality/convention/edge-case bars (stage 2). Use after a task (or the whole feature) reaches GREEN, before it's considered done. It reads the diff and the upstream artifacts and reports…

genkovich/sdd · 81 tokens

atomic-auditor

Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…

damusix/atomic-claude · 169 tokens

bt6-pr-auditor

Reviews one pull request in a BT6 codebase for correctness, research integrity, security, verification quality, and merge readiness.

elder-plinius/T3MP3ST · 32 tokens

Reviewer

Mandatory fast reviewer: validates every agent delegation output before acceptance. Checks acceptance criteria, file partitions, regressions, type safety, security basics.

monkilabs/opencastle · 30 tokens

security-auditor

Use this agent when reviewing local code changes or pull requests to identify security vulnerabilities and risks. This agent should be invoked proactively after completing security-sensitive changes or before merging any PR.

NeoLabHQ/context-engineering-kit · 40 tokens