> ## Documentation Index
> Fetch the complete documentation index at: https://docs.summerengine.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Verification before completion skill for AI agents

> Run verification and read its output before claiming work done, fixed or passing: evidence first. A Summer Engine skill for AI agents.

`verification-before-completion` is a skill from the [Summer skill library](/mcp/skills): a guide your AI agent reads when the task matches, so it builds the good version on the first try. Run verification and read its output before claiming work done, fixed or passing: evidence first.

| | |
| - | - |
| Status | Stable |
| Domains | Agent workflow, Verification |
| Version | `1.0.3` |
| Engine version | `>=4.6` |
| Recommended set | Yes, installed by `--recommended` |

## When your agent uses it

* About to claim work is complete, fixed, or passing, before committing or creating PRs
* About to report a test, build, or fix as passing without having run the command and read its output

## Install

`summer setup` installs every skill for your agent. To add only this one:

```bash theme={null}
npx -y summer-engine@latest skills install verification-before-completion --agent claude-code
```

Swap `claude-code` for your agent, such as `codex` or `cursor`. See [Skills](/mcp/skills#quick-start) for every option.

## The skill

## 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 |
| Gameplay behaviour works | `RunVerification` probe: pressed the input, read the state back | Script compiles, game boots, diagnostics clean |
| 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 |
| "There's no way to test gameplay, I'll ask the user" | There is. A `RunVerification` probe presses input and reads state back. Ask the user only for what a probe cannot judge. |

## Key Patterns

**Tests:**

```
Good: [Run test command] [See: 34/34 pass] "All tests pass"
Bad: "Should pass now" / "Looks correct"
```

**Regression tests (TDD Red-Green):**

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

**Build:**

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

**Requirements:**

```
Good: Re-read plan → Create checklist → Verify each → Report gaps or completion
Bad: "Tests pass, phase complete"
```

**Agent delegation:**

```
Good: Agent reports success → Check VCS diff → Verify changes → Report actual state
Bad: Trust agent report
```

## Why This Matters

False completion claims cost trust and time:

* The user stops believing your reports.
* Undefined functions ship and crash.
* Missing requirements ship as incomplete features.
* Time goes to redirecting and rework.

## 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.

***

Source: [`library/skills/verification-before-completion/SKILL.md`](https://github.com/SummerEngine/summer/blob/main/library/skills/verification-before-completion/SKILL.md), rendered from `summer-engine@4.3.0` on npm.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.