Verification Before Completion
jnMetaCode/superpowers-zh
Chinese-language rule that bars an agent from claiming work is done, fixed or passing until it has run a verification command and read the output.
A skill your agent uses when about to declare work done, fixed, or passing, before committing or opening PRs - demands executing verification commands and reading their output before making any…
MITAuto-check passed
Install Completion Gate
$ npx skills add NoobyGains/godmode --skill completion-gate -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install NoobyGains/godmode completion-gate --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/NoobyGains/godmode.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/completion-gate .claude/skills/completion-gate && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "completion-gate" agent skill from https://github.com/NoobyGains/godmode/tree/master/skills/completion-gate into .claude/skills/completion-gate/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "completion-gate", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/NoobyGains/godmode/tree/master/skills/completion-gateType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add NoobyGains/godmode --skill completion-gate -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install NoobyGains/godmode completion-gate --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/NoobyGains/godmode.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/completion-gate .agents/skills/completion-gate && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "completion-gate" agent skill from https://github.com/NoobyGains/godmode/tree/master/skills/completion-gate into .agents/skills/completion-gate/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "completion-gate", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add NoobyGains/godmode --skill completion-gate -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install NoobyGains/godmode completion-gate --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/NoobyGains/godmode.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/completion-gate .cursor/skills/completion-gate && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "completion-gate" agent skill from https://github.com/NoobyGains/godmode/tree/master/skills/completion-gate into .cursor/skills/completion-gate/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "completion-gate", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/NoobyGains/godmode.git --path skills/completion-gate--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add NoobyGains/godmode --skill completion-gate -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install NoobyGains/godmode completion-gate --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/NoobyGains/godmode.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/completion-gate .gemini/skills/completion-gate && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "completion-gate" agent skill from https://github.com/NoobyGains/godmode/tree/master/skills/completion-gate into .gemini/skills/completion-gate/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "completion-gate", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install NoobyGains/godmode completion-gateInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add NoobyGains/godmode --skill completion-gate -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/NoobyGains/godmode.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/completion-gate .github/skills/completion-gate && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "completion-gate" agent skill from https://github.com/NoobyGains/godmode/tree/master/skills/completion-gate into .github/skills/completion-gate/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "completion-gate", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add NoobyGains/godmode --skill completion-gate -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install NoobyGains/godmode completion-gate --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/NoobyGains/godmode.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/completion-gate .opencode/skills/completion-gate && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "completion-gate" agent skill from https://github.com/NoobyGains/godmode/tree/master/skills/completion-gate into .opencode/skills/completion-gate/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "completion-gate", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
completion-gate- GitHub stars
- 107
- Token cost
- ~1.6k tokens
- SKILL.md length
- 523 words
- Files
- 1
- Skills in repo
- 34
- Repo updated
- First seen
- Licence
- MIT
At a glance
A skill your agent uses when about to declare work done, fixed, or passing, before committing or opening PRs - demands executing verification commands and reading their output before making any…
- About to declare work done
- SKILL.md covers Overview, The Prime Directive, The Entry Protocol and Verification Requirements, plus 8 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
- Before committing
What it does
Completion Gate is an agent skill from NoobyGains/godmode. Use when about to declare work done, fixed, or passing, before committing or opening PRs - demands executing verification commands and reading their output before making any success assertions; evidence precedes claims always
Its SKILL.md is about 1.6k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
The repository describes itself as: The AI development framework that thinks before it builds. 36 composable skills for Claude Code, Cursor, Codex, and OpenCode. The licence is MIT.
When your agent uses it
- About to declare work done
- Before committing
- Opening PRs - demands executing verification commands and reading their output before making any success assertions
- Evidence precedes claims always
Example prompts
- “/completion-gate”
What it can do on your machine
Read from SKILL.md and the folder at commit 441103a. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Completion Gate loads about 1.6k tokens when it runs. Until then it costs about 60 tokens; SKILL.md has 523 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from NoobyGains/godmode at commit 441103a, republished under its MIT licence (© NoobyGains). 523 words, ~1,600 tokens.
Download SKILL.mdSave it as
.claude/skills/completion-gate/SKILL.md (or your agent's skills folder).- name
- completion-gate
- description
- Use when about to declare work done, fixed, or passing, before committing or opening PRs - demands executing verification commands and reading their output before making any success assertions; evidence precedes claims always
Completion Gate
Overview
Declaring work complete without verification is dishonesty, not efficiency.
Core principle: Evidence precedes assertions, always.
No exceptions. No workarounds. No shortcuts.
The Prime Directive
NO COMPLETION ASSERTIONS WITHOUT FRESH VERIFICATION OUTPUTIf the verification command has not been executed in this message, you cannot assert it passes.
The Entry Protocol
BEFORE asserting any status or expressing confidence:
1. IDENTIFY: Which command substantiates this assertion?
2. EXECUTE: Run the FULL command (fresh, complete)
3. INSPECT: Read every line of output, check exit code, tally failures
4. CONFIRM: Does the output support the assertion?
- If NO: Report actual status with evidence
- If YES: State the assertion WITH supporting evidence
5. ONLY THEN: Make the assertion
Skipping any step = fabrication, not verificationVerification Requirements
| Assertion | Demands | Insufficient |
|---|---|---|
| Tests pass | Test runner output showing 0 failures | Prior run, "should pass" |
| Linter clean | Linter output showing 0 errors | Partial scan, extrapolation |
| Build succeeds | Build command with exit code 0 | Linter passing, log fragments |
| Bug resolved | Original symptom tested and passes | Code modified, assumed fixed |
| Regression test valid | Red-green cycle confirmed | Single green pass |
| Agent finished | VCS diff showing actual changes | Agent self-reported "done" |
| Specification met | Line-by-line requirement checklist | Tests passing alone |
Guardrails - HALT
- Using hedging language: "should", "probably", "seems to"
- Expressing premature satisfaction ("Done!", "Perfect!", "All good!")
- About to commit/push/open PR without verification
- Trusting an agent's self-reported success
- Relying on partial or stale verification
- Thinking "just this one time"
- Fatigued and wanting to wrap up
- ANY phrasing that implies success without having run verification
Cognitive Traps
| Rationalization | Truth |
|---|---|
| "Should work now" | EXECUTE the verification |
| "I'm confident" | Confidence is not evidence |
| "Just this once" | No exceptions |
| "Linter passed" | Linter is not the compiler |
| "Agent reported success" | Verify independently |
| "I'm tired" | Fatigue is not justification |
| "Partial check is enough" | Partial proof is no proof |
| "Different wording so rule doesn't apply" | Intent over technicality |
Verification Patterns
Tests:
CORRECT: [Run test command] [Output: 34/34 pass] "All tests pass"
WRONG: "Should pass now" / "Looks correct"Regression tests (Red-Green cycle):
CORRECT: Write -> Run (pass) -> Revert fix -> Run (MUST FAIL) -> Restore -> Run (pass)
WRONG: "I've written a regression test" (without red-green confirmation)Build:
CORRECT: [Run build] [Output: exit 0] "Build passes"
WRONG: "Linter passed" (linter does not validate compilation)Specification compliance:
CORRECT: Re-read plan -> Create checklist -> Verify each item -> Report gaps or completion
WRONG: "Tests pass, phase done"Agent delegation:
CORRECT: Agent reports done -> Check VCS diff -> Verify changes -> Report actual state
WRONG: Trust agent report at face valueVerifying Configuration Changes
When testing changes to configuration, providers, feature flags, or environment settings:
Do not merely confirm the operation succeeded. Confirm the output reflects the intended change.
The Silent Fallback Problem
An operation can succeed because some valid configuration exists, even if it is not the configuration you intended to apply.
| Change | Insufficient | Required |
|---|---|---|
| Switch LLM provider | HTTP 200 | Response body contains expected model identifier |
| Toggle feature flag | No errors | Feature behavior observably active |
| Change environment | Deployment succeeds | Logs/variables reference the new environment |
| Set credentials | Authentication succeeds | Authenticated identity is the correct one |
Show full SKILL.md (184 more words)Show less
Configuration Verification Sequence
BEFORE asserting a configuration change works:
1. IDENTIFY: What should be DIFFERENT after this change?
2. LOCATE: Where is that difference observable?
3. EXECUTE: Command that exposes the observable difference
4. CONFIRM: Output contains the expected difference
5. ONLY THEN: Assert the configuration change works
Warning signs:
- "Request succeeded" without inspecting content
- Checking status code but ignoring response body
- Confirming no errors but lacking positive confirmationVerifying UI Work
When asserting UI work is complete:
| Assertion | Demands | Insufficient |
|---|---|---|
| Component matches design | Visual comparison against UX reference | "It looks right to me" |
| Responsive design works | Tested at mobile, tablet, desktop breakpoints | Desktop-only check |
| Accessibility passes | Screen reader test + keyboard navigation + contrast check | "I added aria labels" |
| Design tokens applied | Spacing/colors/typography match token values | "I used the right classes" |
Why This Matters
From accumulated failure patterns:
- your human partner said "I don't believe you" — trust shattered
- Undefined functions shipped — immediate 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 or completion claims
- ANY expression of satisfaction
- ANY positive statement about work state
- Committing, PR creation, task completion
- Transitioning to the next task
- Delegating to agents
Rule applies to:
- Exact phrases
- Paraphrases and synonyms
- Implications of success
- ANY communication suggesting completion or correctness
The Bottom Line
There are no shortcuts for verification.
Execute the command. Read the output. THEN state the result.
This is non-negotiable.
© NoobyGains, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in skills/completion-gate of NoobyGains/godmode.
Open the folder on GitHubat commit 441103a
Compare with similar skills
Completion Gate next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Completion Gate this skillNoobyGains/godmode | 107 | — | ~1.6k | Automated safety check: Pass | MIT | |
| Verification Before CompletionjnMetaCode/superpowers-zh | 8.3k | — | ~443 | Automated safety check: Pass | MIT | |
| Fixalirezarezvani/claude-skills | 28k | 1 repos | ~765 | Automated safety check: Pass | MIT | |
| Orch Fix Defectaffaan-m/ECC | 275k | 1 repos | ~414 | Automated safety check: Pass | MIT | |
| Gate Testsvercel/next.js | 143k | — | ~2.7k | Automated safety check: Pass | MIT | |
| Verification Before Completionforyourhealth111-pixel/Vibe-Skills | 3.6k | — | ~1.1k | Automated safety check: Pass | Apache-2.0 |
Similar skills
Fix
alirezarezvani/claude-skills
Fix failing or flaky Playwright tests. An agent skill from alirezarezvani/claude-skills.
Orch Fix Defect
affaan-m/ECC
Orchestrate fixing a bug — reproduce it as a failing regression test, fix to green, review, and gated commit — by delegating each phase to the matching ECC agent.
- Official
Gate Tests
vercel/next.js
How to use the @gate / @force-gate test directives instead of it.skip or fake-green skip patterns.
Verification Before Completion
foryourhealth111-pixel/Vibe-Skills
Completion-evidence route used before claiming work is complete, fixed, passing, committed, or PR-ready.
Delivery Gate
affaan-m/ECC
Stop hook that blocks Claude from finishing until quality checks pass.
More from NoobyGains/godmode
All 34 skills in this repoActivation
NoobyGains/godmode
A skill your agent uses when starting any conversation - establishes how to locate and invoke skills, mandating Skill tool usage before ANY response including clarifying questions
Agent Messaging
NoobyGains/godmode
A skill your agent uses when dispatching subagents, composing prompts for teammates, structuring handoff reports, or managing context boundaries between agents.
Codebase Research
NoobyGains/godmode
A skill your agent uses when building ANY feature within an existing project - search the current codebase for existing patterns, conventions, similar implementations, and established approaches…
Comprehension Check
NoobyGains/godmode
A skill your agent uses when implementing any substantial feature, multi-file modification, or architectural change - produces a plain-language walkthrough of every alteration so the developer can…
Delegated Execution
NoobyGains/godmode
A skill your agent uses when executing implementation plans with independent tasks in the current session
Deployment Advisor
NoobyGains/godmode
A skill your agent uses when making technology, hosting, or infrastructure decisions — recommends services, databases, and deployment strategies based on project requirements and what the user…
Questions about Completion Gate
What does Completion Gate do?
A skill your agent uses when about to declare work done, fixed, or passing, before committing or opening PRs - demands executing verification commands and reading their output before making any…. Completion Gate is an agent skill from NoobyGains/godmode.
When should I use Completion Gate?
Completion Gate fits situations like: about to declare work done; before committing; opening PRs - demands executing verification commands and reading their output before making any success assertions; evidence precedes claims always.
How do I install Completion Gate in Claude Code?
Run `npx skills add NoobyGains/godmode --skill completion-gate -a claude-code`. Or copy the skill folder (skills/completion-gate in NoobyGains/godmode) into .claude/skills/completion-gate in your project. Claude Code loads it when a task matches its description.
How do I install Completion Gate in Codex?
Run `npx skills add NoobyGains/godmode --skill completion-gate -a codex`. Or copy the skill folder (skills/completion-gate in NoobyGains/godmode) into .agents/skills/completion-gate in your project. Codex loads it when a task matches its description.
Can I use Completion Gate in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add NoobyGains/godmode --skill completion-gate -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/completion-gate, .gemini/skills/completion-gate, .github/skills/completion-gate and .opencode/skills/completion-gate in your project.
What does Completion Gate need to run?
SKILL.md names no scripts, command-line tools or credentials: Completion Gate is instructions for the agent only.
Does Completion Gate access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Completion Gate safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Completion Gate use?
Completion Gate is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Completion Gate use?
About 1.6k tokens (SKILL.md is roughly 6.4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Completion Gate?
Skills that share tags, products or a category with Completion Gate: Verification Before Completion (jnMetaCode/superpowers-zh, 8.3k stars), Fix (alirezarezvani/claude-skills, 28k stars), Orch Fix Defect (affaan-m/ECC, 275k stars) and Gate Tests (vercel/next.js, 143k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Completion Gate?
NoobyGains (a GitHub user) maintains it in NoobyGains/godmode, which has 107 GitHub stars. The repository holds 34 skills in this directory. The repository was last updated on March 9, 2026.
Source: NoobyGains/godmode on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.