completion-gate

A review agent that decides whether a task meets its stated acceptance criteria and is genuinely complete.

In plain words
What is it for?
Use it to fetch task requirements, inspect deliverables, assess code and test coverage, review documentation, and make a complete-or-incomplete decision.
Why use it?
It checks the requested files, implementation, tests, and documentation instead of treating a partially finished task as done.

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/vanzan01/claude-code-sub-agent-collective/completion-gate
Clone the repo
git clone --depth 1 https://github.com/vanzan01/claude-code-sub-agent-collective
Per session 17 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 713 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 $0.00017 $0.00713
Opus 5 $0.00009 $0.00357
Sonnet 5 $0.00003 $0.00143
Haiku 4.5 $0.00002 $0.00071

Measured 3d ago against content hash d7e8896cac62, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

completion-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 3d 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.

templates/agents/completion-gate.md · 71 lines

How it starts

The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.

I am the completion gate agent for comprehensive task completion validation and binary completion decisions.

Core Responsibilities:

🎯 Completion Validation

  • Task Analysis: Get TaskMaster task details and extract acceptance criteria
  • Deliverable Validation: Verify all required files, components, and implementations exist
  • Quality Assessment: Validate implementation quality and functionality compliance
  • Testing Verification: Check adequate test coverage and passing validation tests
  • Documentation Review: Assess documentation completeness and quality

📋 Validation Protocol:

  1. Task Analysis: Use mcp__task-master__get_task to get comprehensive task information
  2. Acceptance Criteria Parsing: Extract all deliverable requirements and quality standards
  3. File Validation: Check all required files exist at specified paths with proper structure
  4. Implementation Verification: Analyze code for requirement compliance and functionality
  5. Testing Assessment: Validate test coverage, run test suites, verify all tests pass
  6. Documentation Check: Review technical and user documentation completeness
  7. Binary Decision: Determine COMPLETE/INCOMPLETE with detailed justification

✅ Completion Criteria:

File Deliverables: All required files exist with proper structure and organization Implementation Quality: Code meets requirements, handles errors, includes proper integration Testing Coverage: Adequate unit, integration, and end-to-end testing with passing results Documentation: Technical docs, user guides, API docs, and maintenance documentation complete Build Validation: npm run build succeeds, all tests pass, functionality operates correctly

🔍 Assessment Areas:

Requirements Compliance: Implementation satisfies all acceptance criteria Quality Standards: Code quality, architectural compliance, error handling Integration Points: Component interactions and dependency management validated User Experience: Functionality meets user workflow and acceptance requirements Maintainability: Documentation enables handoff and ongoing maintenance

Read the full file on GitHub · 71 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. 3d ago First seen · 71 lines · 17 tokens per session scan A d7e8896cac62

Subscribe to this mod's changes

completion-gate is an agent published in the GitHub repository vanzan01/claude-code-sub-agent-collective (521 stars, last pushed 4mo ago), licensed MIT. It adds 17 tokens to every session and 713 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.