01 / Summary

What this skill teaches your AI coding agent

Verification Before Completion functions as a stop-the-line mechanism for autonomous engineering agents. Unconstrained agents frequently declare success prematurely, assuming their proposed changes will work without verifying compilation or running tests. This protocol blocks the agent from outputting completion signals until four gates pass: static type-checking and linting with zero warnings, automated test runner execution returning exit code 0, inspection of git diff to clean up debug statements, and a smoke verification of application boot.

✦ DIRECT ANSWERCITABLE DEFINITION

Verification Before Completion is an open-source testing skill licensed under MIT that blocks agents from declaring tasks complete until all tests, types, and diffs pass.

✓ Use it if

You need strict, reproducible guardrails enforcing testing & qa discipline across agent interactions.

✕ Skip it if

You are building quick disposable prototypes where architectural consistency and test verification are unnecessary.

02 / When It Triggers

Activation boundaries & prompt triggers

Autonomous Activation TriggerToken Tax: ~420 tk

Prompts that fire this skill:

💬 "User prompts: "Strict verification gate prohibiting agents from declaring tasks complete u...""
💬 "Agent is about to declare work complete, fixed, passing, or ready for merge."
💬 "When autonomous agent needs strict protocol guardrails"

Hard Negative Invariants (Agent Guardrails):

⛔ Execute full build command and test suite; confirm 0 exit code before making success assertions.
⛔ Inspect browser console logs and DOM element rendering on live dev server.
⛔ Provide concrete command output evidence rather than unverified verbal claims.

03 / Installation

Inject into Claude.ai, Claude Code, or Cursor

Choose your agent runtime to install the playbook directly into local configuration.

.cursor/rules/verification-before-completion.mdc

MARKDOWN19 lines

1---
2description: Strict verification gate prohibiting agents from declaring tasks complete until linting, typechecking, tests, and diff checks pass.
3globs: *
4alwaysApply: false
5---
6
7# Verification Before Completion Gate
8
9STOP: You are prohibited from declaring a task complete, finished, or resolved until you have executed and reported the results of the following verification sequence:
10
111. TYPE-CHECK & LINT:
12   - Execute project linter and type-checker (`tsc --noEmit`, `npm run lint`).
13   - ZERO errors or unhandled warnings allowed.
142. TEST SUITE EXECUTION:
15   - Execute the full test suite for modified modules.
16   - Witness all assertions green with exit code 0.
173. GIT DIFF SANITY:
18   - Run `git diff` and self-review every modified line.
19   - Confirm removal of debug prints, scratch files, and temporary code.

04 / What's Inside

Interactive file tree manifest & playbook viewer

Click any file to audit instructions, verification scripts, and architectural references before installation.

SKILL.md

---
name: verification-before-completion
description: "Strict verification gate prohibiting agents from declaring tasks complete until linting, typechecking, tests, and diff checks pass."
version: 1.0.0
license: MIT
compatibility: [claude-3-5-sonnet, cursor, windsurf, cline]
---

# Verification Before Completion Protocol

Verification Before Completion functions as a stop-the-line mechanism for autonomous engineering agents. Unconstrained agents frequently declare success prematurely, assuming their proposed changes will work without verifying compilation or running tests. This protocol blocks the agent from outputting completion signals until four gates pass: static type-checking and linting with zero warnings, automated test runner execution returning exit code 0, inspection of git diff to clean up debug statements, and a smoke verification of application boot.

## Core Guardrails
- ⛔ Execute full build command and test suite; confirm 0 exit code before making success assertions.
- ⛔ Inspect browser console logs and DOM element rendering on live dev server.
- ⛔ Provide concrete command output evidence rather than unverified verbal claims.

## Autonomous Activation Triggers
When user prompts:
- "User prompts: "Strict verification gate prohibiting agents from declaring tasks complete u...""
- "Agent is about to declare work complete, fixed, passing, or ready for merge."
- "When autonomous agent needs strict protocol guardrails"

05 / Before & After

Verified behavioral proof of work

Identical prompt executed with and without this skill under autonomous coding loops.

✦ BEHAVIORAL PROOF OF WORK

Execute Verification Before Completion Protocol under autonomous coding loops

Token Footprint1,350 tokens89% Token Savings

Files Mutated1 file

Execution VerdictDeterministic Pass

Guarded Agent Loop:

Strict negative invariants enforced: Execute full build command and test suite; confirm 0 exit code before making success assertions.. Deterministic verification pass.

git diff --stat (1 file, minimal patch)

1diff --git a/src/app.ts b/src/app.ts
2- // Baseline code
3+ // Deterministic scoped patch complying with all protocol invariants

06 / Security & Script Audit

Execution safety and file access boundaries

⚠ Code Execution Audit Warning

Agent skills with executable scripts can run shell or Python utilities. Always audit scripts before execution.

Scope: Bound to active workspace branch.
Network Calls: Zero outbound network calls.
AST Syntax Gate: Pre-flight verification blocks breaking mutations.

07 / Troubleshooting

Operational triage & resolution runbook

✦ OPERATIONAL RUNBOOKField Triage

⚠Skill not triggering during user conversational prompt▼

Probable Root Cause:

Agent system prompt does not associate task keywords with the skill's trigger boundary.

Recommended Fix:

Reference the skill name explicitly in your prompt (e.g., "Follow the rules in verification-before-completion to perform this refactoring").

⚠Conflicting rules with root project instructions▼

Probable Root Cause:

Global instructions (.cursorrules or CLAUDE.md) contradict the skill's invariants.

Recommended Fix:

Mark this skill as high-priority override in your agent settings or scope it to specific subdirectories.

⚠Context window saturation warning▼

Probable Root Cause:

Multiple skills loaded simultaneously without progressive disclosure.

Recommended Fix:

Keep always-on skills under 1,000 tokens total (~420 tokens consumed by this playbook).

08 / Decision Rubric

Skill vs. MCP Server vs. Plain System Prompt

Primitive	Best Used When	Token Cost	Execution Risk
Agent Skill (`SKILL.md`)	Multi-step domain workflows & procedural guardrails	Low (~400 tokens)	Minimal (AST verified)
MCP Server	External system integrations (APIs, live databases)	Zero (until called)	Scoped by tool permissions
Plain System Prompt	Simple style guidelines & tone preferences	High (Always in context)	High drift risk