agentmods.dev

verify-change

verify-change is a skill for Claude Code from LS-SIEM-LLP/qa-probe. It costs 66 tokens per session (578 once invoked), scanned A, original, Apache-2.0.

A verification procedure for a changed web application. It uses qa-probe to find affected pages and API endpoints, test the running application, and report whether checks passed, failed, or could not be completed.

In plain words
What is it for?
Use it after changing a web app that has a qa-probe configuration, especially when checking selected files, all known endpoints, or stricter checks in continuous integration.
Why use it?
It helps catch broken behaviour after editing frontend or backend code instead of relying only on the code compiling. The result includes evidence and identifies what was not checked.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the qa-probe plugin — 1 skill shipped together

not rated 2repo 2d ago A scan 66 tokens original Apache-2.0

Good fit Use it after changing a web app that has a qa-probe configuration, especially when checking selected files, all known endpoints, or stricter checks in continuous integration.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ls-siem-llp/qa-probe/verify-change
View source ↗ LS-SIEM-LLP/qa-probe npmjs.com
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 LS-SIEM-LLP/qa-probe --skill verify-change
Clone the repo
git clone --depth 1 https://github.com/LS-SIEM-LLP/qa-probe

Made for: Claude Code.

Or install qa-probe, the plugin that ships this one along with the rest of its 1 skill.

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-change

README.md
[![agentmods](https://agentmods.dev/badge/skills/ls-siem-llp/qa-probe/verify-change/github.svg)](https://agentmods.dev/skills/ls-siem-llp/qa-probe/verify-change)
Your own site
<a href="https://agentmods.dev/skills/ls-siem-llp/qa-probe/verify-change"><img src="https://agentmods.dev/badge/skills/ls-siem-llp/qa-probe/verify-change/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 verify-change

Your own site · 80×15
<a href="https://agentmods.dev/skills/ls-siem-llp/qa-probe/verify-change"><img src="https://agentmods.dev/badge/skills/ls-siem-llp/qa-probe/verify-change.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 66 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 578 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 $0.00066 $0.00578
Opus 5.5 $0.00026 $0.00231
Sonnet 5.5 $0.00013 $0.00116
Haiku 4.5 $0.00007 $0.00058

Measured yesterday against content hash 1c3ee9e537ed, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

verify-change 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 yesterday.

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.

claude-plugin/skills/verify-change/SKILL.md · 45 lines

What it actually says

Verify a change with qa-probe

Use this after you edit frontend or backend code in a project that has a qa-probe.config.js (or after the user asks whether the running app still works).

Run it

From the project root, with the files you changed (comma separated, relative to the project root):

npx -y [email protected] verify --files path/one.tsx,path/two.py --json
  • Leave out --files to use the files changed in git.
  • Add --all to probe every known endpoint.
  • Add --strict when "inconclusive" should count as a failure (for example in CI).
  • If it says there is no graph yet, run npx -y [email protected] analyze once, or npx -y [email protected] run.
  • To check the setup first: npx -y [email protected] doctor.

qa-probe needs a config file and a backend it can reach. If the project has no qa-probe.config.js, tell the user and point them to https://github.com/LS-SIEM-LLP/qa-probe#readme. Never guess or invent credentials; the test account belongs in the project's own config or environment.

Read the result honestly

The JSON has verdict, confidence, endpoints, notChecked and summary.

  • pass: at least one affected endpoint was verified healthy and none is broken. Look at notChecked for what was not exercised (write endpoints are never exercised).
  • fail: something probed live is broken. Report the endpoint, its status and fixHint, and fix it before saying the change works. The command also exits with a non-zero code.
  • inconclusive: nothing affected could be verified. Do not claim success. Say what could not be checked, then try --all or ask the user.

A 200 response with no data, a 401 or 403 for the test account, and long-lived streams are reported as not verified, never as failures. Files that map to no page or endpoint are listed in notChecked instead of being guessed at.

qa-probe never changes data and never edits source files.

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. yesterday First seen · 45 lines · 66 tokens per session scan A 1c3ee9e537ed

Subscribe to this mod's changes

verify-change is a skill published in the GitHub repository LS-SIEM-LLP/qa-probe (2 stars, last pushed 2d ago), licensed Apache-2.0. It adds 66 tokens to every session and 578 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-11-10.

E2E testingTestingai-agentsapi-testingdevtoolsfastapimcpnodejs
Related

verify-change compared with skills from other repositories

verify-change next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
verify-changeLS-SIEM-LLP/qa-probeSkill22d agoApache-2.0A66Claude Code
playwright-cliVoltAgent/voltagentSkill11k5d agoMITA52Claude Code
verify-bbget-bb/bbSkill5.3ktodayMITA70Claude Code, Codex
create-verification-skillget-bb/bbSkill5.3ktodayMITA57Claude Code, Codex
maintain-verification-skillget-bb/bbSkill5.3ktodayMITA53Claude Code, Codex
JMeter Load TestingPramodDutta/qaskillsSkill2488d agoMITA32Claude Code, Codex
api-testingidavidov13/agentic-playwrightSkill2808d agoMITA69Claude Code, Codex