Verification Before Completion

Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always

Security Scan

The skill is an instruction-only checklist that consistently instructs agents to run and report verification commands before claiming completion — its requirements match its stated purpose.

Purpose & Capability

The name/description and SKILL.md all focus on running verification commands and reporting evidence; there are no unrelated env vars, binaries, or installs requested.

Instruction Scope

The instructions explicitly tell the agent to identify and run the verification command and to read full output/exit codes. This is coherent with the purpose, but intentionally open-ended: the agent is given discretion to choose and execute commands on the environment. That is expected for verification tasks but can be risky if the agent is allowed to run destructive/high-privilege commands without additional constraints or user confirmation.

Install Mechanism

No install spec or code files are present; the skill is instruction-only, so nothing is written to disk or fetched during install.

Credentials

The skill requests no environment variables, credentials, or config paths. The SKILL.md's references (e.g., VCS diffs, test output) are relevant and proportional to verification work.

Persistence & Privilege

Defaults are used (not always:true). The skill can be invoked autonomously by agents (platform default), which is normal; combined with the instruction to run commands, users should be mindful of agent execution privileges, but there is no explicit attempt to persist or escalate privileges.

Assessment

This skill is coherent and focused: it enforces a 'run the command and show the output' pattern before claiming work is done. Before installing, consider how the agent is allowed to execute commands on your system: ideally require explicit user confirmation before running any commands that can modify state or require elevated privileges, enable logging of verification runs, and limit the agent's execution environment (sandbox, container, or read-only mode) if possible. If you want stricter controls, modify the skill or your agent policy so every verification command is presented for approval before execution.

Overview

Claiming work is complete without verification is dishonesty, not efficiency.

Core principle: Evidence before claims, always.

Violating the letter of this rule is violating the spirit of this rule.

The Iron Law

NO COMPLETION CLAIMS WITHOUT FRESH VERIFICATION EVIDENCE

If you haven't run the verification command in this message, you cannot claim it passes.

The Gate Function

BEFORE claiming any status or expressing satisfaction:

1. IDENTIFY: What command proves this claim?
2. RUN: Execute the FULL command (fresh, complete)
3. READ: Full output, check exit code, count failures
4. VERIFY: Does output confirm the claim?
   - If NO: State actual status with evidence
   - If YES: State claim WITH evidence
5. ONLY THEN: Make the claim

Skip any step = lying, not verifying

Common Failures

Claim	Requires	Not Sufficient
Tests pass	Test command output: 0 failures	Previous run, "should pass"
Linter clean	Linter output: 0 errors	Partial check, extrapolation
Build succeeds	Build command: exit 0	Linter passing, logs look good
Bug fixed	Test original symptom: passes	Code changed, assumed fixed
Regression test works	Red-green cycle verified	Test passes once
Agent completed	VCS diff shows changes	Agent reports "success"
Requirements met	Line-by-line checklist	Tests passing

Red Flags - STOP

• Using "should", "probably", "seems to"
• Expressing satisfaction before verification ("Great!", "Perfect!", "Done!", etc.)
• About to commit/push/PR without verification
• Trusting agent success reports
• Relying on partial verification
• Thinking "just this once"
• Tired and wanting work over
• ANY wording implying success without having run verification

Rationalization Prevention

Excuse	Reality
"Should work now"	RUN the verification
"I'm confident"	Confidence ≠ evidence
"Just this once"	No exceptions
"Linter passed"	Linter ≠ compiler
"Agent said success"	Verify independently
"I'm tired"	Exhaustion ≠ excuse
"Partial check is enough"	Partial proves nothing
"Different words so rule doesn't apply"	Spirit over letter

Key Patterns

Tests:

✅ [Run test command] [See: 34/34 pass] "All tests pass"
❌ "Should pass now" / "Looks correct"

Regression tests (TDD Red-Green):

✅ Write → Run (pass) → Revert fix → Run (MUST FAIL) → Restore → Run (pass)
❌ "I've written a regression test" (without red-green verification)

Build:

✅ [Run build] [See: exit 0] "Build passes"
❌ "Linter passed" (linter doesn't check compilation)

Requirements:

✅ Re-read plan → Create checklist → Verify each → Report gaps or completion
❌ "Tests pass, phase complete"

Agent delegation:

✅ Agent reports success → Check VCS diff → Verify changes → Report actual state
❌ Trust agent report

Why This Matters

From 24 failure memories:

• your human partner said "I don't believe you" - trust broken
• Undefined functions shipped - would crash
• Missing requirements shipped - incomplete features
• Time wasted on false completion → redirect → rework
• Violates: "Honesty is a core value. If you lie, you'll be replaced."

When To Apply

ALWAYS before:

• ANY variation of success/completion claims
• ANY expression of satisfaction
• ANY positive statement about work state
• Committing, PR creation, task completion
• Moving to next task
• Delegating to agents

Rule applies to:

• Exact phrases
• Paraphrases and synonyms
• Implications of success
• ANY communication suggesting completion/correctness

The Bottom Line

No shortcuts for verification.

Run the command. Read the output. THEN claim the result.

This is non-negotiable.