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.
npx skills add stunt-double/stuntdouble-mcp --skill verify-changegit clone --depth 1 https://github.com/stunt-double/stuntdouble-mcpWrote 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.
[](https://agentmods.dev/skills/stunt-double/stuntdouble-mcp/verify-change)<a href="https://agentmods.dev/skills/stunt-double/stuntdouble-mcp/verify-change"><img src="https://agentmods.dev/badge/skills/stunt-double/stuntdouble-mcp/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.
<a href="https://agentmods.dev/skills/stunt-double/stuntdouble-mcp/verify-change"><img src="https://agentmods.dev/badge/skills/stunt-double/stuntdouble-mcp/verify-change.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00033 | $0.00742 |
| Opus 5 | $0.00016 | $0.00371 |
| Sonnet 5 | $0.00007 | $0.00148 |
| Haiku 4.5 | $0.00003 | $0.00074 |
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 9d 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.
How it starts
The opening of the file, as written. The whole thing — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Verify change
When to use
- A code change has landed on a preview deployment, staging, or production and needs checking before merge or release
- A PR has a preview URL and you want evidence the change works and nothing adjacent regressed
- You want a reusable regression suite for a flow, not a one-off manual pass
Instructions
-
Resolve context:
list_workspaces()→ pick the workspace (use it silently if there is only one)list_projects(workspace_id)→ match the preview URL or product name against an existing project. Tools that take aurl(likecreate_checklist) will find or create the project for you.
-
Pick an actor:
list_actors(workspace_id)→ reuse a QA-style actor if one existscreate_actor(...)if the workspace has none; a plain "QA tester" actor is fine
-
Create a checklist against the preview URL:
create_checklist(...)with the preview URL as the hostinstructions— describe how to exercise the changed flows as a real user wouldchecks— specific pass/fail statements covering: the new behaviour works, adjacent flows did not regress, and error states behave. 4–8 checks is the sweet spot.
-
Run and poll:
run_checklist(checklist_id)→ returns a run ID (async)get_checklist_run(run_id)→ poll every 30–60s until terminal. Each check result carries evidence.
-
Report:
- If any check fails, summarise the failure with its evidence and the likely fix. If you can edit the code, offer to fix and re-run the same checklist against the updated preview.
- If a pull request is associated with the change, post the results with
comment_on_pr(owner/repo#number): a short verdict line, then a table of checks with pass/fail and evidence highlights.
-
Keep it as a regression suite:
- Suggest re-running the checklist on the next change to this area, or wire it to a schedule or GitHub events with
create_workflow(see thesetup-guardrailsskill).
- Suggest re-running the checklist on the next change to this area, or wire it to a schedule or GitHub events with
Example output
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.
- 9d ago First seen · 60 lines · 33 tokens per session scan A f1eb6b4cbd69
verify-change is a skill published in the GitHub repository stunt-double/stuntdouble-mcp (1 stars, last pushed 24d ago), licensed MIT. It adds 33 tokens to every session and 742 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.
Other skills, from other repositories
screen-reader-testing
Test web applications with screen readers including VoiceOver, NVDA, and JAWS. Use when validating screen reader compatibility, debugging accessibility issues, or ensuring assistive technology support.
e2e-testing-patterns
Master end-to-end testing with Playwright and Cypress to build reliable test suites that catch bugs, improve confidence, and enable fast deployment. Use when implementing E2E tests, debugging flaky tests, or establishing testing standards.
browser-testing-with-devtools
Tests in real browsers via Chrome DevTools MCP. Use when building or debugging anything that runs in a browser. Use when you need to inspect the DOM, capture console errors, analyze network requests, profile performance, or verify visual output with real runtime data. Requires the chrome-devtools MCP server to be…
designing-tests
Designs and implements testing strategies for any codebase. Use when adding tests, improving coverage, setting up testing infrastructure, debugging test failures, or when asked about unit tests, integration tests, or E2E testing.
qa/e2e-playwright
A method for writing Playwright end-to-end tests, which automate a browser to verify complete user journeys. It covers setup, reusable page objects, login reuse, API mocking, visual checks, multiple browsers and screen sizes, CI, and debugging.
backend/testing-guide
A guide for writing backend tests: small unit tests, tests that check connected parts such as an API and database, and end-to-end tests that follow a complete user flow.