verify-before-done

verify-before-done is a skill for Claude Code, Codex from buildmoonshot/skillpacks. It costs 60 tokens per session (384 once invoked), scanned A, original, MIT.

A completion check that requires evidence before an agent says a code change is finished or working.

In plain words
What is it for?
It helps verify changes by running tests, builds, scripts, or concrete logic traces, and by reporting whether verification passed, failed, or was not possible.
Why use it?
It prevents untested changes from being reported as successful based only on expectation.

Skill for Claude CodeCodex

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/buildmoonshot/skillpacks/verify-before-done
Any agent
npx skills add buildmoonshot/skillpacks --skill verify-before-done
Clone the repo
git clone --depth 1 https://github.com/buildmoonshot/skillpacks

Made for: Claude Code, Codex.

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-before-done

README.md
[![agentmods](https://agentmods.dev/badge/skills/buildmoonshot/skillpacks/verify-before-done.svg)](https://agentmods.dev/skills/buildmoonshot/skillpacks/verify-before-done)
Your own site
<a href="https://agentmods.dev/skills/buildmoonshot/skillpacks/verify-before-done"><img src="https://agentmods.dev/badge/skills/buildmoonshot/skillpacks/verify-before-done.svg" alt="Measured on agentmods" height="20"></a>
Per session 60 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 384 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 $0.00060 $0.00384
Opus 5 $0.00030 $0.00192
Sonnet 5 $0.00012 $0.00077
Haiku 4.5 $0.00006 $0.00038

Measured 4d ago against content hash a95d521bee3e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

verify-before-done 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.

skills/engineering/beginner/verify-before-done/SKILL.md · 31 lines

What it actually says

Verify Before Done

Do not say a change is "done," "fixed," or "working" until you have evidence that it is.

What counts as evidence

In rough order of strength:

  1. Run it. Execute the test, build, script, or command that exercises the change and read the actual output.
  2. Add a check. If nothing tests this path, write a small test or assertion that would fail before your fix and pass after — then run it.
  3. Trace it. If you genuinely can't run anything, walk the changed logic step by step with a concrete example input and show the result. Say explicitly that this is a trace, not an execution.

How to report

  • If it passed: say so, and briefly say what you ran ("ran npm test — 14 passing").
  • If it failed: say that plainly and show the output. A failure you report is a problem solved; a failure you hide is a problem shipped.
  • If you couldn't verify: say "I couldn't verify this because ___" instead of implying it works. Never let an unverified change wear the word "done."

The rule

"Should work" is not "works." If you didn't check, don't claim it.

Why this matters

The most expensive bug is the one the agent confidently called "fixed." Verification converts confident guesses into either a real result or an honest "not yet" — both of which save the user from discovering the failure in production.

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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 · 31 lines · 60 tokens per session scan A a95d521bee3e

Subscribe to this mod's changes

verify-before-done is a skill published in the GitHub repository buildmoonshot/skillpacks (2 stars, last pushed 2mo ago), licensed MIT. It adds 60 tokens to every session and 384 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

bridge

Use when the user wants hyperflow's behavioral rules to apply outside the terminal CLI — in Claude Code Desktop, claude.ai web, or IDE extensions that don't load CLI plugins. Writes a managed doctrine block into the project's CLAUDE.md so autonomy + intent-routing + commit cadence + role separation + file-first rules…

jeremylongshore/tons-of-skills-marketplace · 126 tokens

fable-method

A step-by-step problem-solving loop (classify the ask, define done, gather evidence, decide, act surgically, verify by observation, report outcome-first). Use when the user says "/fable-method", "use the fable method", or "approach this like Fable", or proactively when starting any multi-step task that no…

Sahir619/fable-method · 105 tokens

fable-domain

Discuss a domain with the user, research it from real sources, then generate a trusted skill bundle for it - a step-by-step workflow with a flowchart, a domain adapter, a trap fixture, and a smoke eval. Use when the user says "/fable-domain ", "make a skill for ", "add a domain to the fable method", or "give a lesser…

Sahir619/fable-method · 115 tokens

writers-pattern

Add a new platform writer module in src/writers/ that generates and writes agent config files for a supported platform. Each writer exports a function that accepts a config interface, creates directories (rules/, skills/, mcp configs), writes files with proper formatting and frontmatter, and returns string[] of…

caliber-ai-org/ai-setup · 111 tokens

caliber-testing

Writes Vitest tests following project patterns: tests/ directories, vi.mock() for module mocking with vi.hoisted() for test-time factories, global LLM mock from src/test/setup.ts, environment variable save/restore in beforeEach/afterEach, vi.clearAllMocks() lifecycle, and test file organization. Use when user says…

caliber-ai-org/ai-setup · 113 tokens

llm-provider

Adds a new LLM provider implementing LLMProvider interface with call() and stream() methods. Integrates with provider factory in src/llm/index.ts, config detection in src/llm/config.ts, and error handling via tracking and recovery. Use when adding a new model backend, integrating a third-party LLM API, or extending…

caliber-ai-org/ai-setup · 100 tokens