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 OpenEvident/vindicate --skill skillgit clone --depth 1 https://github.com/OpenEvident/vindicateWrote 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/openevident/vindicate/skill)<a href="https://agentmods.dev/skills/openevident/vindicate/skill"><img src="https://agentmods.dev/badge/skills/openevident/vindicate/skill/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/openevident/vindicate/skill"><img src="https://agentmods.dev/badge/skills/openevident/vindicate/skill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00077 | $0.01150 |
| Opus 5.5 | $0.00031 | $0.00460 |
| Sonnet 5.5 | $0.00015 | $0.00230 |
| Haiku 4.5 | $0.00008 | $0.00115 |
Grade A, and why
vindicate 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 1mo 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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Vindicate — Playwright Test Automation
You produce grounded, conformant Playwright tests through Vindicate's workflow. Engage this whenever the user wants to write / add / fix / stabilize / refactor / run / audit tests, find coverage gaps, or set up Playwright automation or CI. For general coding, docs, or questions, work directly — don't use Vindicate tools.
Start every task by orienting
-
Call
vindicate_workflow()(no args) → map + empty progress panel. Pick the entry path:- write / add tests →
write - fix a specific broken test →
fix - stabilize a flaky / intermittent test →
flaky - refactor tests (no behavior change) →
refactor - find missing coverage by exploring the app →
gaps - report AC coverage from stories vs specs (no exploration) →
coverage - run existing tests against a URL →
smoke - draft requirements/a story only from a recording (no tests) →
requirements - scaffold a project from scratch →
bootstrap - add or fix Playwright CI →
ci
If the task is genuinely ambiguous, ask the user which path (one question).
- write / add tests →
-
Start the path:
vindicate_workflow(path="write", node="understand", completed=[])(swap path/node for your task). -
Each phase change: when the current node done-conditions are met, call the next node with
completedupdated — add the node you just finished:vindicate_workflow(path="write", node="ground", from="understand", completed=["understand"])Always copy
progress_echofrom the last response into the next call (path,node,completed). -
Read
phase_instructionsin each tool result — mandatory phase steps at the top; workflow-tool field rules in the appended section. Followprogress_display.instructionexactly (server detects whether this client renders the MCP App panel). Useagent_directivesforprogress_echo, done-conditions, and the next call. -
Branches are allowed (e.g. execute → heal → ground) — update
node,from, andcompletedto match where you are; the panel shows heal when you enter it.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 1mo ago First seen · 79 lines · 77 tokens per session scan A d867683d124c
vindicate is a skill published in the GitHub repository OpenEvident/vindicate (45 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 77 tokens to every session and 1,150 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 2026-08-30.
Other skills, from other repositories
selectors
Selector strategy, exploration-first workflow, locator priority order (getByRole then getByLabel then getByPlaceholder then getByText then getByTestId), and feedback/validation-message selector rules for Playwright page objects. Use when creating page objects, writing or updating locators, generating UI tests, or…
playwright-cli
Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.
debugging
Playwright test debugging conventions for the scaffold — reading failure messages, classifying failure modes (TimeoutError, ZodError, strict-mode violation, locator not found, network errors, schema drift), the playwright.config.ts capture defaults (trace on-first-retry, screenshot only-on-failure, video…
api-testing
API testing patterns for Playwright -- apiRequest fixture usage, Zod response schema creation and validation, test.step wrapping for multi-call tests, per-field negative/validation testing, path parameter fuzzing, and helper fixtures for shared setup/teardown. Use when writing or updating API test specs, adding tests…
page-objects
Page Object Model pattern for the Playwright scaffold — class structure, get-accessor locator pattern, action-method conventions, component composition, registration via the page-object fixture, and the mandatory exploration-first workflow. Use when creating a new page object, adding or updating locators on an…
test-standards
Spec file conventions for the Playwright scaffold — imports from test-options.ts, test file structure (describe / beforeEach / test / test.step), single-tag rule, functional vs E2E vs API vs setup test types, data-driven test loops against TS static data, web-first assertions, destructive-test cleanup, and test…