verification-before-completion

verification-before-completion is a skill for Claude Code from brunob54/superpowers-orchestrator. It costs 47 tokens per session (975 once invoked), scanned A, original, MIT.

A final-check procedure for confirming a coding task is really complete. It requires fresh command output as evidence before claiming that tests pass, a build works, or a bug is fixed.

In plain words
What is it for?
It identifies and runs the command that proves the result, inspects its exit status and output, checks applicable conditions, and scans for TODO, FIXME, placeholder, or unimplemented code.
Why use it?
It prevents completion claims based on old results, assumptions, or another agent's report. It also checks changed production code for common unfinished placeholders.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions subagents.

Part of the superpowers-orchestrator plugin — 28 skills, 2 agents, 6 hooks shipped together

Good fit It identifies and runs the command that proves the result, inspects its exit status and output, checks applicable conditions, and scans for TODO, FIXME, placeholder, or unimplemented code.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/brunob54/superpowers-orchestrator/verification-before-completion
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.

Any agent
npx skills add brunob54/superpowers-orchestrator --skill verification-before-completion
Clone the repo
git clone --depth 1 https://github.com/brunob54/superpowers-orchestrator

Made for: Claude Code.

Or install superpowers-orchestrator, the plugin that ships this one along with the rest of its 28 skills, 2 agents, 6 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 verification-before-completion

README.md
[![agentmods](https://agentmods.dev/badge/skills/brunob54/superpowers-orchestrator/verification-before-completion/github.svg)](https://agentmods.dev/skills/brunob54/superpowers-orchestrator/verification-before-completion)
Your own site
<a href="https://agentmods.dev/skills/brunob54/superpowers-orchestrator/verification-before-completion"><img src="https://agentmods.dev/badge/skills/brunob54/superpowers-orchestrator/verification-before-completion/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for verification-before-completion

Your own site · 80×15
<a href="https://agentmods.dev/skills/brunob54/superpowers-orchestrator/verification-before-completion"><img src="https://agentmods.dev/badge/skills/brunob54/superpowers-orchestrator/verification-before-completion.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 47 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 975 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00047 $0.00975
Opus 5 $0.00023 $0.00487
Sonnet 5 $0.00009 $0.00195
Haiku 4.5 $0.00005 $0.00097

Measured 8d ago against content hash 8c94aa155566, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

verification-before-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 8d 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.

skills/verification-before-completion/SKILL.md · 112 lines

How it starts

The opening of the file, as written. The whole thing — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Verification Before Completion

Do not claim success without fresh command evidence.

Gate

Before any completion claim:

  1. Identify the command that proves the claim.
  2. Run the full command now.
  3. Inspect exit code and output.
  4. State results exactly as observed.
  5. If the change includes a condition or gate that determines when something applies: explicitly state what it does NOT cover. If the answer reveals a gap that should be covered, fix it before proceeding.

Applies To

  • "Tests pass"
  • "Bug is fixed"
  • "Build succeeds"
  • "Ready to merge"
  • Any equivalent wording

Not Acceptable

  • "Should pass"
  • "Looks good"
  • Trusting old outputs
  • Trusting subagent reports without verification

Minimum Evidence Examples

  • Tests: command output with zero failures
  • Build: successful exit code
  • Bugfix: reproduction case now passes
  • Requirements: explicit checklist against plan

Stub Scan (Implementation Tasks)

When verifying completion of any task that created or modified production code, run a stub scan before claiming done:

grep -rn "TODO\|FIXME\|placeholder\|NotImplementedError\|raise NotImplementedError" <src-dir> \
  --include="*.ts" --include="*.js" --include="*.py" --include="*.go" --include="*.rs" \
  | grep -v -i "test\|spec\|__tests__"

Adjust <src-dir> and --include patterns to the project's language and source structure. If any match falls in a file this task created or modified: the task is not done. Remove the stub or confirm with the user it is intentional before claiming completion.

Regression Test Verification (Red-Green Cycle)

When verifying a bugfix with a regression test, the test must prove it catches the bug:

✅ Write test → Run (PASS) → Revert fix → Run (MUST FAIL) → Restore fix → Run (PASS)
❌ "I've written a regression test" (without red-green verification)

A regression test that has never been seen failing proves nothing — it might pass for the wrong reason.

Agent Delegation Verification

Read the full file on GitHub · 112 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. 8d ago First seen · 112 lines · 47 tokens per session scan A 8c94aa155566

Subscribe to this mod's changes

verification-before-completion is a skill published in the GitHub repository brunob54/superpowers-orchestrator (3 stars, last pushed 2d ago), licensed MIT. It adds 47 tokens to every session and 975 once invoked, about $0.0002 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.