What is workclaw-change-verification?

A verification guide for changes in the WorkClaw project. It maps the part of the project that changed to the smallest test or build command that can check it.

Use it after changing React, Tauri, Rust packages, sidecars, built-in skills, build behavior, or user flows to choose and run the relevant tests and builds.

It helps avoid claiming that a change works without running checks appropriate to its runtime, backend, skills, packaging, or user-facing behavior.

How haojing8312/WorkClaw configures Claude Code and Codex

Reuse

Borrowing it

Nothing to install: this file belongs to haojing8312/WorkClaw. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/haojing8312/WorkClaw/main/.agents/skills/workclaw-change-verification/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/haojing8312/WorkClaw

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/haojing8312/workclaw/workclaw-change-verification.svg)](https://agentmods.dev/skills/haojing8312/workclaw/workclaw-change-verification)

Your own site

<a href="https://agentmods.dev/skills/haojing8312/workclaw/workclaw-change-verification"><img src="https://agentmods.dev/badge/skills/haojing8312/workclaw/workclaw-change-verification.svg" alt="Measured on agentmods" height="20"></a>

Per session 36 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 492 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.

Model	Per session	Once invoked
Fable 5.1	$0.00036	$0.00492
Opus 5	$0.00018	$0.00246
Sonnet 5	$0.00007	$0.00098
Haiku 4.5	$0.00004	$0.00049

Measured 8d ago against content hash 69dc363f2ea1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

workclaw-change-verification 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.

.agents/skills/workclaw-change-verification/SKILL.md · 61 lines

How it starts

The opening of the file, as written. The whole thing — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.

WorkClaw Change Verification

Overview

Use this skill to decide what "verified" means for the changed area in WorkClaw. Reuse the repo's existing commands and run the smallest command set that honestly covers the touched surface.

When to Use

React runtime code changed
Tauri backend code changed
Sidecar runtime or adapters changed
Rust package logic changed
Builtin skill assets or skill-related crates changed
Build or test behavior changed
UI flows changed in a way that can affect user behavior

Do not use this for docs-only changes that cannot affect runtime, tests, packaging, or build behavior.

Command Routing

Use pnpm test:sidecar for apps/runtime/sidecar/ changes.
Use pnpm test:rust-fast for apps/runtime/src-tauri/ or packages/* Rust logic changes.
Use pnpm test:builtin-skills for builtin skill asset or skill crate changes.
Use pnpm test:e2e:runtime for user-facing runtime flows that need end-to-end coverage.
Use pnpm build:runtime when desktop packaging, build output, or integration boundaries may be affected.

When multiple surfaces changed, combine the relevant commands instead of picking only one.

Required Output

Commands run
Pass or fail results
Which changed areas were covered by each command
Any areas still unverified
Whether it is valid to claim the work is verified

Output Template

Use this shape:

## Verification Summary
- Changed surface:
- Commands run:
- Results:
- Covered areas:
- Still unverified:
- Verification verdict:

Core Pattern

Map changed files to runtime surface areas.
Select the smallest honest command set.
Run the commands before claiming completion.
Report verification concretely, not vaguely.

Common Mistakes

Saying "verified" after reading tests without running them.
Running only frontend tests for a change that also affects Tauri or sidecar behavior.
Forgetting pnpm test:builtin-skills when skill assets or skill-related crates changed.

Read the full file on GitHub · 61 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.

8d ago First seen · 61 lines · 36 tokens per session scan A 69dc363f2ea1

Subscribe to this mod's changes

workclaw-change-verification is a skill published in the GitHub repository haojing8312/WorkClaw (140 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 36 tokens to every session and 492 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.

Testing

research-engineer

An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.

davila7/claude-code-templates · 43 tokens

tika-eval-compare

Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".

apache/tika · 50 tokens

neuron-evaluation-engineer

Create and run AI evaluations with datasets, assertions, and output drivers in Neuron AI. Use this skill whenever the user mentions evaluation, testing AI systems, creating evaluators, dataset-driven testing, assertion-based validation, or wants to measure AI system performance. Also trigger for tasks involving…

neuron-core/neuron-ai · 77 tokens

WorkClaw: Skill for Claude Code