verification-before-completion
An agent skill by obra, from obra/superpowers. Tags: api, developer-tools, web.
What it does
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
Install
With the skills CLI, which installs into Claude Code, Codex, Cursor and other agents:
npx skills add obra/superpowers --skill verification-before-completionOr copy the skill folder into Claude Code's skills directory by hand (~/.claude/skills for every project, or .claude/skills inside one):
git clone --depth 1 https://github.com/obra/superpowers
cp -r superpowers/skills/verification-before-completion ~/.claude/skills/verification-before-completionSafety box score
Grade A, minimal risk: 0 of 100 risk points, rated 2026-10-21. The grade rates what the skill and its scripts can reach on the machine of whoever installs it, across eight categories from shell execution to secrets access. How the score works.
This is a policy-only skill: it contains guidance about verifying work before making completion claims, and it ships no executable code. The main effect is on agent behavior and wording, not on the machine, network, files, or accounts.
| Category | Level | Why |
|---|---|---|
| Code & shell execution | 0 (none) | `SKILL.md` contains only prose and examples; there are no shell commands, scripts, or code to execute. |
| Network access | 0 (none) | No network calls, downloads, or remote data transmission are described anywhere in the skill. |
| Filesystem reach | 0 (none) | It does not read, write, or delete files; the only file present is the markdown guide itself. |
| Secrets & credentials | 0 (none) | There is no handling of tokens, passwords, `.env` files, keychains, or other credentials. |
| Privilege & persistence | 0 (none) | The skill does not request sudo, global installs, services, shell startup edits, or other privilege changes. |
| Instruction hijack surface | 0 (none) | The text does the opposite of prompt injection: it emphasizes verification discipline with lines like `NO COMPLETION CLAIMS WITHOUT FRESH VERIFICATION EVIDENCE` and does not instruct the agent to ignore rules or hidden instructions. |
| Irreversible actions | 0 (none) | It does not push, deploy, publish, send messages, pay, or book anything; it only governs when the agent may claim success. |
| Transparency | 0 (none) | There are no binaries, blobs, generated installers, or unreadable assets; the entire skill is plain markdown. |
Before installing
- Confirm the skill folder contains only `SKILL.md` and no scripts, binaries, or installer hooks.
Rated 2026-10-21 by an automated review of 1 file from the skill's repository.
Source
- Repository
- obra/superpowers (all skills from this repository)
- Path
- skills/verification-before-completion/SKILL.md
- Branch
- main
- Updated
- 2026-09-19
Related skills
- executing-plans — Use when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution.
- finishing-a-development-branch — Use when implementation is complete, all tests pass, and you need to decide how to integrate the work
- receiving-code-review — Use when receiving code review feedback, before implementing suggestions.
- requesting-code-review — Use when completing tasks, implementing major features, or before merging to verify work meets requirements
- systematic-debugging — Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes
- test-driven-development — Use when implementing any feature or bugfix, before writing implementation code