verify-completion

verify-completion is a skill for Claude Code, Codex from hknc/claude-evolve. It costs 59 tokens per session (1,128 once invoked), scanned A, original, MIT.

A completion-checking workflow for reviewing whether a coding task is truly finished before you say it is or commit the changes.

In plain words
What is it for?
Use it for final checks before committing, shipping, or reporting a task as done.
Why use it?
It helps catch missed requirements, edge cases, unfinished cleanup, and incomplete error handling that a quick review may overlook.

Skill for Claude CodeCodex

Part of the claude-evolve plugin — 13 skills, 8 commands, 9 agents, 4 hooks shipped together

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/hknc/claude-evolve/verify-completion
Any agent
npx skills add hknc/claude-evolve --skill verify-completion
Clone the repo
git clone --depth 1 https://github.com/hknc/claude-evolve

Made for: Claude Code, Codex.

Or install claude-evolve, the plugin that ships this one along with the rest of its 13 skills, 8 commands, 9 agents, 4 hooks.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for verify-completion

README.md
[![agentmods](https://agentmods.dev/badge/skills/hknc/claude-evolve/verify-completion.svg)](https://agentmods.dev/skills/hknc/claude-evolve/verify-completion)
Your own site
<a href="https://agentmods.dev/skills/hknc/claude-evolve/verify-completion"><img src="https://agentmods.dev/badge/skills/hknc/claude-evolve/verify-completion.svg" alt="Measured on agentmods" height="20"></a>
Per session 59 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,128 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00059 $0.01128
Opus 5 $0.00030 $0.00564
Sonnet 5 $0.00012 $0.00226
Haiku 4.5 $0.00006 $0.00113

Measured 4d ago against content hash ac4dc4bb4e16, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

verify-completion scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

plugins/claude-evolve/skills/verify-completion/SKILL.md · 187 lines

How it starts

The opening of the file, as written. The whole thing — 187 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Verify Completion Skill

You systematically verify work is actually complete before claiming done.

Philosophy

  • Evidence over feeling - "I think it's done" -> "I verified it's done"
  • Original requirements - Check against what was asked, not what was built
  • Edge cases - The obvious path works, but what about edges?
  • Clean state - No debug code, no TODOs, no temporary hacks

Process

1. Recall Original Requirements

First, explicitly state what was requested:

  • What did the user originally ask for?
  • Were there any clarifications or changes?
  • What's the acceptance criteria?

2. Run Verification Checklist

Go through systematically:

## Completion Verification

### Requirements Check
- [ ] Original requirement met: [state it]
- [ ] All clarifications addressed: [list any]
- [ ] Scope creep avoided: [nothing extra added]

### Code Quality (if applicable)
- [ ] No debug code (console.log, print, debugger)
- [ ] No commented-out code
- [ ] No hardcoded values that should be config
- [ ] No TODO/FIXME/HACK comments left
- [ ] Error handling complete

### Testing
- [ ] Happy path works
- [ ] Edge cases handled: [list them]
- [ ] Error cases handled: [list them]
- [ ] Tests pass (if test suite exists)

### Integration
- [ ] Works with existing code
- [ ] No breaking changes (or documented)
- [ ] Dependencies updated if needed

### Cleanup
- [ ] Temporary files removed
- [ ] Git status clean (only intended changes)
- [ ] No unrelated changes mixed in

3. Verify Evidence

For each check, verify with evidence:

# No debug statements
grep -r "console.log\|print(\|debugger" src/

# Tests pass
npm test  # or equivalent

# Git status clean
git status
git diff --stat

4. Check Edge Cases

For the specific feature, identify and test edges:

Feature Type Common Edge Cases
Input handling Empty, null, very long, special chars
Lists Empty list, single item, many items
Numbers Zero, negative, very large, decimals
Dates Boundaries, timezones, leap years
Auth No token, expired, invalid, wrong permissions
Files Missing, empty, too large, wrong format

Read the full file on GitHub · 187 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 4d ago First seen · 187 lines · 59 tokens per session scan A ac4dc4bb4e16

Subscribe to this mod's changes

verify-completion is a skill published in the GitHub repository hknc/claude-evolve (8 stars, last pushed 7mo ago), licensed MIT. It adds 59 tokens to every session and 1,128 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens