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 britt/agent-skills --skill writing-verification-plansgit clone --depth 1 https://github.com/britt/agent-skillsWrote 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/britt/agent-skills/writing-verification-plans)<a href="https://agentmods.dev/skills/britt/agent-skills/writing-verification-plans"><img src="https://agentmods.dev/badge/skills/britt/agent-skills/writing-verification-plans/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/britt/agent-skills/writing-verification-plans"><img src="https://agentmods.dev/badge/skills/britt/agent-skills/writing-verification-plans.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 | $0.00055 | $0.00923 |
| Opus 5 | $0.00028 | $0.00462 |
| Sonnet 5 | $0.00011 | $0.00185 |
| Haiku 4.5 | $0.00006 | $0.00092 |
Grade A, and why
writing-verification-plans 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 10d 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 — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Writing Verification Plans
Overview
Help Claude write verification plans that validate a project works in real-world scenarios before completing tasks.
Core principle: Verification is not integration testing. It uses real systems, never mocks or fakes. A test environment is acceptable only if it's a fully running copy of the system being integrated with.
Announce at start: "I'm using the writing-verification-plans skill to create acceptance testing procedures."
When to Use This Skill
Use this skill when:
- Setting up a new project (called from
setting-up-a-projectskill) - A project lacks a VERIFICATION_PLAN.md
- The developer asks for a verification plan
- Adding new features that require real-world validation
When NOT to use: Not for writing automated test suites — this skill produces manual/agent-executed acceptance procedures, not unit or integration tests.
Writing the Verification Plan
Ask the user about the real-world scenarios that need to be validated. For each scenario, gather:
- What is being tested? The feature or capability to verify
- What does success look like? Concrete, observable outcomes
- What environment is needed? Real systems, test accounts, sample data
- What could go wrong? Edge cases and failure modes to check
VERIFICATION_PLAN.md Format
# Verification Plan
**Verification runs automatically after completing any task. Do not wait for the developer to request it.**
## Prerequisites
[List everything needed before verification can run]
- Test environment setup instructions
- Required accounts or credentials
- Sample data or test fixtures
- External systems that must be running
## Scenarios
### Scenario 1: [Name]
**Context**: [What state the system should be in before starting]
**Steps**:
1. [Specific action Claude should take]
2. [Next action]
3. [Continue until complete]
**Success Criteria**:
- [ ] [Observable outcome that must be true]
- [ ] [Another required outcome]
**If Blocked**: [When to stop and ask developer for help]
[Add a section like Scenario 1 for each additional scenario]
## Verification Rules
- Never use mocks or fakes
- Test environments must be fully running copies of real systems
- If any success criterion fails, verification fails
- Ask developer for help if blocked, don't guess
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.
- 10d ago First seen · 134 lines · 55 tokens per session scan A 0366a7028c15
writing-verification-plans is a skill published in the GitHub repository britt/agent-skills (5 stars, last pushed 7d ago), licensed MIT. It adds 55 tokens to every session and 923 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.
Other skills, from other repositories
dogfood
Systematically explore and test a mobile app on iOS/Android with agent-device to find bugs, UX issues, and other problems. Use when asked to dogfood, QA, exploratory test, find issues, bug hunt, or test this app on mobile.
test-warp-ui
Guides testing Warp UI features and changes using the computer use tool. Use this skill only when computer-use testing was requested (explicit request or accepted offer) and the computeruse tool is available to the agent. Covers launching Warp and verifying UI behavior.
test-electron-app
Drive the real running PostHog Electron app (live tRPC, workspace-server, real data) over CDP with agent-browser. Connect to the running app on port 9222, test desktop changes against a local Django stack, snapshot the accessibility tree, inspect network requests, and screenshot only when explicitly asked. Use when…
pyats-dynamic-test
Generate and execute deterministic pyATS aetest validation scripts - interface state, OSPF neighbors, BGP paths, ping matrices, and custom compliance tests. Use when writing a network test, validating post-change state, running pass/fail checks, or building automated regression tests.
test-loop
Plan, generate, and heal an executable E2E test suite from approved acceptance criteria (web and mobile).
playwright-cli
Automates browser interactions for testing and validating your own web applications using playwright-cli. Use when you need terminal-first browser control for navigation, form filling, screenshots, tracing, bound browser sessions, debugging, or generating Playwright test code. Only use against applications you own or…