gate-check

gate-check is a skill for Claude Code from phj128/autoworker. It costs 55 tokens per session (1,437 once invoked), scanned A, original, MIT.

A final review procedure for an autoworker task before completion is reported. It reads the task record, checks test evidence against acceptance criteria, assesses confidence, and records a pass or fail result.

In plain words
What is it for?
Use it after implementation and testing are finished, when a task has a subtask record. It checks test results, acceptance criteria, confidence levels, and the final routing decision.
Why use it?
It catches missing tests or unsupported completion claims before work is handed over. Items below the required confidence level receive additional verification.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the autoworker plugin — 10 skills, 1 command shipped together

Good fit Use it after implementation and testing are finished, when a task has a subtask record. It checks test results, acceptance criteria, confidence levels, and the final routing decision.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/phj128/autoworker/gate-check
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.

Any agent
npx skills add phj128/autoworker --skill gate-check
Clone the repo
git clone --depth 1 https://github.com/phj128/autoworker

Made for: Claude Code.

Or install autoworker, the plugin that ships this one along with the rest of its 10 skills, 1 command.

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-check

README.md
[![agentmods](https://agentmods.dev/badge/skills/phj128/autoworker/gate-check.svg)](https://agentmods.dev/skills/phj128/autoworker/gate-check)
Your own site
<a href="https://agentmods.dev/skills/phj128/autoworker/gate-check"><img src="https://agentmods.dev/badge/skills/phj128/autoworker/gate-check.svg" alt="Measured on agentmods" height="20"></a>
Per session 55 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,437 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00055 $0.01437
Opus 5 $0.00028 $0.00718
Sonnet 5 $0.00011 $0.00287
Haiku 4.5 $0.00006 $0.00144

Measured 8d ago against content hash cb5199f04064, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

gate-check scanned grade A with 1 finding 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 8d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- "API might not work" → curl it — NOT "requires user confirmation"
skills/gate-check/SKILL.md · 143 lines

How it starts

The opening of the file, as written. The whole thing — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.

autoworker:gate-check — Pre-Completion Self-Check (Gate 3)

Trigger: Called by autoworker:dispatch when all tests are complete. Pure assessment skill — does not make routing decisions.

Execution Flow

1. Pre-Check

Glob `subtask_*.md` (exclude subtask_template.md) →
  0 found → stop, prompt to create subtask
  1 found → use directly (backward compatible)
  multiple → grep `status:` to filter:
    - Files without status field treated as active (backward compatible)
    - Exactly 1 active → use it
    - 0 active → list all files + status, prompt user to choose
    - >1 active → report anomaly
→ Read → check "Test Results" section
  • Test results section is empty → FAIL, prompt to complete tests and call autoworker:checkpoint first
  • Has test results → continue

1.5. Acceptance Criteria Traceability

Read subtask's "Acceptance Criteria" table, check whether each metric was measured in L1-L4 test results:

  • Metric not measured → that change point's confidence < 95% (Step 3 will trigger supplementary verification)
  • All metrics have corresponding test results → continue
  • No acceptance criteria table (legacy subtask format) → skip this step

2. Fill Confidence Assessment Table

In subtask.md's "Confidence Assessment" section, fill in for each change point:

Change point Test level Confidence Verification method Unverified/Risk

Confidence inference basis:

  • Has L4 pass + meaningful output → 95%+
  • Has L2 but no L4 → 70-85%
  • Only L1 → 50-70%
  • Untested → 30%

3. Supplementary Verification for < 95% Items

When the table above has < 95% items:

  1. Design supplementary verification commands (specific, executable)
  2. Execute immediately
  3. Fill in results
  4. Update confidence

Record in subtask.md's "< 95% Supplementary Verification" table.

Boundary for "requires user confirmation" — only scenarios depending on human senses qualify:

  • "Selector may have changed" → launch browser and check — NOT "requires user confirmation"
  • "API might not work" → curl it — NOT "requires user confirmation"
  • "Config might be wrong" → write a script to load and check — NOT "requires user confirmation"
  • UI appearance, interaction feel → legitimate "requires user confirmation"

Read the full file on GitHub · 143 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. 8d ago First seen · 143 lines · 55 tokens per session scan A cb5199f04064

Subscribe to this mod's changes

gate-check is a skill published in the GitHub repository phj128/autoworker (18 stars, last pushed 5mo ago), licensed MIT. It adds 55 tokens to every session and 1,437 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.