Verified:GitHub

verification-before-completion

Enforce evidence-based verification before any completion claim.

Updated May 4, 2026

Search Tags:#testing #verification #evidence #quality-assurance #claims #build-validation

One-click install

npx skills add https://github.com/xaionaro/.config-codex --skill verification-before-completion-xaionaro

Or copy as Structured Prompt for Agent▼

Please help me install this Agent Skill.
Skill: verification-before-completion
Source: https://github.com/xaionaro/.config-codex/tree/main/skills/verification-before-completion
Command: npx skills add https://github.com/xaionaro/.config-codex --skill verification-before-completion-xaionaro

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

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.

Core Features & Use Cases

The Iron Law demands verification evidence be fresh and complete before any completion claim. The Gate Function prescribes a step-by-step approach:

IDENTIFY: What command proves this claim?
RUN: Execute the FULL command (fresh, complete)
READ: Full output, check exit code, count failures
VERIFY: Does output confirm the claim? If not, report status with evidence; If yes, report claim with evidence
ONLY THEN: Make the claim Skipping steps leads to unverified results and undermines honesty and efficiency.

The Iron Law

NO COMPLETION CLAIMS WITHOUT FRESH VERIFICATION EVIDENCE

The Gate Function

BEFORE claiming any status or expressing satisfaction:

IDENTIFY: What command proves this claim?
RUN: Execute the FULL command (fresh, complete)
READ: Full output, check exit code, count failures
VERIFY: Does output confirm the claim?
ONLY THEN: Make the claim

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"

Quick Start

Run the verification workflow to ensure all steps are completed before marking success.

Frequently Asked Questions about verification-before-completion

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I verify code changes before claiming a task is complete?▼

Completion claims require fresh verification evidence obtained by executing a proving command, reading the full output, checking the exit code, and confirming zero failures before asserting success.

What is evidence-based build validation in software development?▼

Evidence-based build validation requires running the full build command fresh, reading the complete output, and confirming a zero exit code before claiming the build succeeds.

Why does my testing workflow report success but tests still fail?▼

False success occurs when completion claims rely on previous runs, partial checks, or agent reports. You must execute the full test command fresh and count zero failures directly from the current output.

How do I stop making unverified completion claims during development?▼

To stop making unverified completion claims, follow the gate function: identify the proving command, run it fully, read the output, verify the results match your claim, and only then make the claim.

Is passing a linter sufficient evidence to claim a build succeeds?▼

Passing a linter is not sufficient evidence to claim a build succeeds. A linter passing does not equal a compiler passing; you must execute the build command and verify a zero exit code independently.