gate-checker

gate-checker is an agent for Claude Code from stevesolun/micro-skills. It costs 24 tokens per session (353 once invoked), scanned A, original, MIT.

An independent reviewer that checks files or directories against quality questions and project instructions. It answers each question yes or no, treating uncertainty or partial success as a failure.

In plain words
What is it for?
Use it to inspect completed code or files for correctness, requirements, usability, integration, and project-specific checks.
Why use it?
It reviews the result with fresh context, helping catch problems that the person or agent who built it may overlook.

Agent for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: model in frontmatter.

Part of the micro-skill-pipeline plugin — 1 skill, 7 commands, 1 agent, 2 hooks shipped together

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/stevesolun/micro-skills/gate-checker
Clone the repo
git clone --depth 1 https://github.com/stevesolun/micro-skills

Made for: Claude Code.

Or install micro-skill-pipeline, the plugin that ships this one along with the rest of its 1 skill, 7 commands, 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 gate-checker

README.md
[![agentmods](https://agentmods.dev/badge/agents/stevesolun/micro-skills/gate-checker.svg)](https://agentmods.dev/agents/stevesolun/micro-skills/gate-checker)
Your own site
<a href="https://agentmods.dev/agents/stevesolun/micro-skills/gate-checker"><img src="https://agentmods.dev/badge/agents/stevesolun/micro-skills/gate-checker.svg" alt="Measured on agentmods" height="20"></a>
Per session 24 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 353 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 $0.00024 $0.00353
Opus 5 $0.00012 $0.00177
Sonnet 5 $0.00005 $0.00071
Haiku 4.5 $0.00002 $0.00035

Measured 5d ago against content hash 943895882fdb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

gate-checker 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.

micro-skill-pipeline/agents/gate-checker.md · 36 lines

What it actually says

You are a gate checker. Your ONLY job is to answer YES or NO to quality gate questions.

You have NO context about how this output was built. You are seeing it fresh. This is intentional -- the builder is biased toward seeing what they expect. You are not.

Instructions

  1. Read the output file(s) at $ARGUMENTS. If no path was provided, ask the user: "Which file or directory should I review?"
  2. Read check-gates.md if it exists in the project root or .claude/.
  3. Read failure-log.md if it exists.
  4. Answer every gate question YES or NO. Be strict.
    • If you're unsure, the answer is NO.
    • "It's fine for now" is NO.
    • "Mostly works" is NO.
  5. For each NO, state what is wrong in one sentence.
  6. Return your results as a structured list.

Universal Gate Questions

  1. Does the output match what was requested?
  2. Are all stated constraints satisfied?
  3. Does every element serve a purpose?
  4. Is the output usable as-is with no manual fixes?
  5. If code: does it compile/run without errors?
  6. If file: is the format correct and complete?
  7. If multi-component: do components integrate correctly?

Then answer all questions from check-gates.md and check against failure-log.md patterns.

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 · 36 lines · 24 tokens per session scan A 943895882fdb

Subscribe to this mod's changes

gate-checker is an agent published in the GitHub repository stevesolun/micro-skills (11 stars, last pushed 5mo ago), licensed MIT. It adds 24 tokens to every session and 353 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 2026-08-30.