verification-before-completion

verification-before-completion is a skill for Claude Code from jcwleo/oh-no-harness. It costs 38 tokens per session (3,732 once invoked), scanned A, original, MIT.

A completion-checking guide that requires fresh evidence before claiming work is finished, fixed, passing, or safe.

In plain words
What is it for?
It helps check final results against acceptance requirements and test evidence before reporting completion.
Why use it?
It reduces unsupported status claims after code changes, such as saying tests pass without running them in the current work session.

Skill for Claude Code

Written for Claude Code: argument-hint in frontmatter. Also seen: mentions subagents; mentions Claude Code.

Part of the oh-no-harness plugin — 12 skills, 12 commands, 9 agents, 1 hook shipped together

Good fit It helps check final results against acceptance requirements and test evidence before reporting completion.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/jcwleo/oh-no-harness/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 jcwleo/oh-no-harness --skill verification-before-completion
Clone the repo
git clone --depth 1 https://github.com/jcwleo/oh-no-harness

Made for: Claude Code.

Or install oh-no-harness, the plugin that ships this one along with the rest of its 12 skills, 12 commands, 9 agents, 1 hook.

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/jcwleo/oh-no-harness/verification-before-completion/github.svg)](https://agentmods.dev/skills/jcwleo/oh-no-harness/verification-before-completion)
Your own site
<a href="https://agentmods.dev/skills/jcwleo/oh-no-harness/verification-before-completion"><img src="https://agentmods.dev/badge/skills/jcwleo/oh-no-harness/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/jcwleo/oh-no-harness/verification-before-completion"><img src="https://agentmods.dev/badge/skills/jcwleo/oh-no-harness/verification-before-completion.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 38 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,732 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 $0.00038 $0.03732
Opus 5 $0.00019 $0.01866
Sonnet 5 $0.00008 $0.00746
Haiku 4.5 $0.00004 $0.00373

Measured 10d ago against content hash 46eabea5f591, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, 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 10d 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/oh-no-harness/skills-claude/verification-before-completion/SKILL.md · 318 lines

How it starts

The opening of the file, as written. The whole thing — 318 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Verification Before Completion for Claude Code

This generated file is the Claude Code-facing runtime skill document. Claude Code slash commands should read this file directly; maintainers edit the source documents listed below instead.

Generated Runtime Composition

Source order:

  • ../../docs/skill-core/verification-before-completion.md
  • ../../docs/platforms/claude-code-verification-before-completion.md

The sections below are already composed for this platform. Do not ask the runtime model to load another platform's runtime document or invocation syntax.

Source: docs/skill-core/verification-before-completion.md

Verification Before Completion

Do not claim success without fresh evidence. This skill is both a standalone lightweight final gate and the final evidence gate inside ralph and ultrawork — when those stronger workflows are active, verify the final claim without weakening their PRD, review, cleanup, or QA requirements. Do not use it as a substitute for ralph when the work needs PRD tracking, cleanup, and review loops.

Invariants

V1. No completion claim without fresh, acceptance-mapped evidence verified
    in the current work pass; a previous run is not fresh evidence unless
    nothing it depends on changed.
V2. A success status is not acceptance: HTTP 2xx with an empty or error
    body, exit 0 with no state change, or a "done" log line without the
    observable effect is missing evidence, not a pass.
V3. A command list is not proof: every acceptance criterion maps to
    evidence with coverage strength, freshness, and audit status.
V4. An independent `verifier` audit is required only when a named trigger
    fires: an explicit user request; stale, missing, or conflicting evidence;
    a named security, data-loss, destructive, migration, recovery, or
    public-contract risk that actually needs independent evidence; or accepted
    blocking-review fix resolution. Mode, task non-triviality, the current
    agent having authored or accepted the proving tests or implementation,
    reviewer presence, and imminent completion are explicit NON-triggers. When a
    trigger fires, this self-gate never substitutes for that audit.
V9. Fresh revision-bound reviewer, verifier, and command evidence is reused as
    recorded. Completion imminence alone never justifies a rerun, an added
    test, or a fresh dispatch; only stale, missing, or conflicting evidence
    does.
V5. A merge or integration step is evidence-changing unless the caller
    proves the final files and dependencies are identical to the
    verifier-audited state.
V6. Reuse the caller's canonical ledger in place, recording only the delta;
    never rewrite an unchanged parallel acceptance mapping.
V7. Secrets and PII are redacted to labeled placeholders before any
    real-surface artifact, command output, or log is recorded as evidence.
V8. Final evidence gate: return the result to the caller; never chain to
    another workflow skill.

Read the full file on GitHub · 318 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. 10d ago First seen · 318 lines · 38 tokens per session scan A 46eabea5f591

Subscribe to this mod's changes

verification-before-completion is a skill published in the GitHub repository jcwleo/oh-no-harness (11 stars, last pushed 1mo ago), licensed MIT. It adds 38 tokens to every session and 3,732 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 2026-08-30.

Related

Other skills, from other repositories

debug-optimize-lcp

Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…

ChromeDevTools/chrome-devtools-mcp · 99 tokens

systematic-debugging

Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.

open-metadata/OpenMetadata · 37 tokens

diagnose

Trace from a reproduced symptom to the source code that causes it. Pin the specific file and approximate line, rate confidence in the cause and clarity of the fix independently, and always propose a concrete fix.

emdash-cms/emdash · 43 tokens

repro-admin

Reproduce an EmDash admin UI bug. Attach a container, start the demo dev server, drive the admin with agent-browser using the dev-bypass session, and capture the reproduction as screenshots plus a replayable transcript.

emdash-cms/emdash · 48 tokens

log-error-digest

Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…

zebbern/claude-code-guide · 71 tokens

byted-util-volcengine-detect-retry

An orchestration workflow for Volcengine Cloud Detect, a service that checks websites or network endpoints from test locations.

bytedance/agentkit-samples · 101 tokens