verification-before-completion

A completion-checking procedure that requires fresh, concrete evidence before an agent says a task is finished.

In plain words
What is it for?
Use it before reporting completed work, passing tests, successful builds, or verified fixes.
Why use it?
It prevents unsupported claims such as saying tests pass or a fix works without running the relevant checks.

Skill for Claude CodeCodex

Part of the threadwork plugin — 20 skills, 4 commands, 1 agent, 1 hook 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/jpm1118/threadwork/verification-before-completion
Any agent
npx skills add JPM1118/Threadwork --skill verification-before-completion
Clone the repo
git clone --depth 1 https://github.com/JPM1118/Threadwork

Made for: Claude Code, Codex.

Or install threadwork, the plugin that ships this one along with the rest of its 20 skills, 4 commands, 1 agent, 1 hook.

Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,287 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 $0.00000 $0.01287
Opus 5 $0.00000 $0.00643
Sonnet 5 $0.00000 $0.00257
Haiku 4.5 $0.00000 $0.00129

Measured 2d ago against content hash a1323964d66f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 2d 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 · 191 lines

How it starts

The opening of the file, as written. The whole thing — 191 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Verification Before Completion Skill

Enforce honest work practices by requiring concrete evidence before claiming any task is complete.

Core Principle

NO COMPLETION CLAIMS WITHOUT FRESH VERIFICATION EVIDENCE

This is not a suggestion. This is an absolute rule. Violating it undermines the entire workflow.

When to Use This Skill

Use this skill:

  • Before marking ANY Beads task as complete
  • Before reporting task completion to an orchestrator
  • Before claiming a fix works
  • Before saying tests pass

The Gate Function

Before claiming completion, execute this five-step gate:

Step 1: Identify the Verification Command

What command proves the claim? Examples:

  • "Tests pass" → npm test
  • "Build succeeds" → npm run build
  • "Linter clean" → npm run lint
  • "Feature works" → specific manual verification steps

Step 2: Execute the Command Fully

Run the command. Do not skip this step. Do not assume.

npm test

Wait for complete output. Do not interrupt.

Step 3: Read the Complete Output

Read ALL of it. Not just the summary. Look for:

  • Actual pass/fail counts
  • Any warnings
  • Any skipped tests
  • Error messages

Step 4: Verify Output Supports the Claim

Does the output actually prove what you're claiming?

Claim Valid Evidence Invalid Evidence
"Tests pass" "42/42 tests passed" "Tests should pass"
"Build succeeds" "Build completed in 3.2s" "Build usually works"
"No lint errors" "0 errors, 0 warnings" "I ran the linter"
"Feature works" Specific output showing behavior "It seems to work"

Step 5: State the Claim with Evidence

Only now can you claim completion. Include the evidence:

Task complete.
Evidence: npm test → 42/42 tests passed (0 failures, 0 skipped)

Red Flags - STOP IMMEDIATELY

If you catch yourself using these words, STOP:

  • "should"
  • "probably"
  • "seems"
  • "I think"
  • "usually"
  • "assuming"

These indicate you're about to claim without evidence. Go back to Step 1.

Read the full file on GitHub · 191 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. 2d ago First seen · 191 lines · 0 tokens per session scan A a1323964d66f

Subscribe to this mod's changes

verification-before-completion is a skill published in the GitHub repository JPM1118/Threadwork (5 stars, last pushed 8mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,287 tokens. 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