verify-before-saying-done

A checklist for proving that a change really works before calling it done, fixed, working or deployed.

In plain words
What is it for?
Use it after changing code, configuration, containers, services or visual interfaces, and before closing a task or reporting its status.
Why use it?
It prevents guesses based only on looking at files or screens. Each claim must have a check that would show a different result if something were broken.

Skill for Claude CodeCodex

Part of the claude-code-engineering plugin — 47 skills, 1 command, 8 agents, 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/everywan-dev/claude-code-engineering/verify-before-saying-done
Any agent
npx skills add everywan-dev/claude-code-engineering --skill verify-before-saying-done
Clone the repo
git clone --depth 1 https://github.com/everywan-dev/claude-code-engineering

Made for: Claude Code, Codex.

Or install claude-code-engineering, the plugin that ships this one along with the rest of its 47 skills, 1 command, 8 agents, 1 hook.

Per session 34 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,406 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 $0.00034 $0.01406
Opus 5 $0.00017 $0.00703
Sonnet 5 $0.00007 $0.00281
Haiku 4.5 $0.00003 $0.00141

Measured 2d ago against content hash 2fcf89c7e8ef, 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-saying-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 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/verify-before-saying-done/SKILL.md · 131 lines

How it starts

The opening of the file, as written. The whole thing — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Verify before saying done

A check that cannot fail is not a check.

Before the words "done", "fixed", "working" or "deployed" leave you, you have to be able to answer one question:

What did I run that, if this were broken, would have returned something different?

If there is no answer, you have a reading, not a verification. Say so instead.

When to use this

  • You are about to close a task, comment on a ticket, or answer "is it up?"
  • You changed a config, restarted a service, edited a file inside a container
  • You fixed something visual
  • Someone asks you to confirm a state you have not observed since you changed it

The procedure

1. Write the claim as one sentence. Not "the deploy went fine" — "the API returns the new schema version on all four nodes". A vague claim cannot be falsified, which is why vague claims are the ones that survive.

2. Name the failure mode you are ruling out. "If this were broken, what exactly would be wrong?" The answer picks your instrument. Ruling out "the service did not pick up the config" needs the process's own view of its config, not the file on disk.

3. Pick an instrument that observes the claim, not a neighbour of it. Most false verifications are a measurement of something adjacent:

You measured You claimed The gap
The file parses The service loaded it Loading can be rejected after parsing
The file on disk changed The process reads the change Different inode, different file
The port answers The application works Anything can answer a port
It works in staging It works in production Different components, different risk
The CSS says red The user sees red Something else wins the cascade

4. Run it and keep the raw output. Not your summary of it. The count, the status line, the response body, the screenshot. Summaries are where the optimism gets in.

5. Prove the check is live. Break something on purpose — point it at a hostname that does not exist, at a node that is down — and confirm it goes red. A green result from a check you never saw go red tells you nothing about the system, only about the check.

Read the full file on GitHub · 131 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 · 131 lines · 34 tokens per session scan A 2fcf89c7e8ef

Subscribe to this mod's changes

verify-before-saying-done is a skill published in the GitHub repository everywan-dev/claude-code-engineering (2 stars, last pushed 14d ago), licensed Apache-2.0. It adds 34 tokens to every session and 1,406 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.

Related

Other skills, from other repositories

claude-project-manifest

Creates annotated bibliography-style manifests for Claude projects, tracking files, conversation threads, and relationships with unique IDs and annotations. Use when documenting project contents, creating file inventories, tracking conversation history, or building navigable knowledge maps.

organvm-iv-taxis/a-i--skills · 50 tokens

proofpress

Preserve or inspect decision history for Markdown and static HTML knowledge artifacts with Proofpress. Use when creating or accepting a meaningful revision to an ADR, design doc, PRD, README, strategy note, portable .md artifact, or static .html/.htm artifact in a configured repository, or when receiving a file…

chenmingtang830/proofpress · 82 tokens

llm-wiki

Maintain a personal team knowledge base using the LLM Wiki pattern — incremental ingest, query, and lint operations on a layered wiki architecture.

TheSmuks/ai-project-template · 31 tokens

PBE Extractor

Extract invariant principles from any text — find the ideas that survive rephrasing.

live-neon/skills · 21 tokens

Principle Synthesizer

Synthesize invariant principles from 3+ sources — find the core that survives across all expressions.

live-neon/skills · 25 tokens

wiki-lint

Run a deterministic, read-only health check on an Obsidian wiki. Use for lint, vault health check, audit wiki health, find orphans, find dead links, frontmatter audit, provenance audit, or wiki audit. Reports graph, link, frontmatter, provenance-ledger, empty-section, and stale-index findings; it does not reason…

AgriciDaniel/claude-obsidian · 79 tokens