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 HECer/yoke --skill visual-verificationgit clone --depth 1 https://github.com/HECer/yokeWrote 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/hecer/yoke/visual-verification)<a href="https://agentmods.dev/skills/hecer/yoke/visual-verification"><img src="https://agentmods.dev/badge/skills/hecer/yoke/visual-verification/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/hecer/yoke/visual-verification"><img src="https://agentmods.dev/badge/skills/hecer/yoke/visual-verification.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 | $0.00092 | $0.00883 |
| Opus 5.5 | $0.00037 | $0.00353 |
| Sonnet 5.5 | $0.00018 | $0.00177 |
| Haiku 4.5 | $0.00009 | $0.00088 |
Grade A, and why
visual-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 17d 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 — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Visual verification
Unit tests don't see a blank page, an unwired route, a runtime console error, or AI-slop design.
Make the loop's gate catch them by widening verify, since the loop trusts verify as truth.
1. Compose the verify pipeline
Set verify.command (in .yoke/config.yaml) to chain, fail-fast:
<typecheck> && <unit tests> && yoke design-scan . && yoke flow-smoke .
e.g. tsc --noEmit && vitest run && yoke design-scan . && yoke flow-smoke .. Any red step blocks the story.
2. Flow-smoke with the built-in gate
Configure the key user flows once in .yoke/config.yaml:
smoke:
baseUrl: http://localhost:3000
sourceIdentity:
path: /assets/app-specific-static-source.js
sha256: "<replace with SHA-256 of the served bytes>"
flows:
- name: home
path: /
landmark: "main h1"
- name: login
path: /login
landmark: "form"
The example contains a required hash placeholder. Before running production smoke, replace
the resource path with a stable, app-specific source resource and the hash with its actual
64-character lowercase SHA-256. The schema allows the field to be absent for existing
configuration readers; production flow-smoke requires it.
Start the intended server and confirm its checkout/build and port. Fetch the resource from
the effective baseUrl origin, using the exact body bytes returned by the server. Hash those
bytes, not a local source file that a dev server may transform. The resource must return a
successful HTTP response without redirects, finish within five seconds and contain at most
1 MiB. Keep it stable for the whole smoke run. When --url changes the origin, verify that
origin serves the intended build before deriving the pin.
Refresh the expected hash explicitly after an intentional source/build change and after confirming the server serves that change. A mismatch must fail the gate; do not automatically overwrite the expected hash with whatever a port happens to serve. A shared health response or unchanged marker cannot identify changed app code. This static pin proves only that the selected resource matches before and after the run; retain the checkout fingerprint and acceptance evidence for broader source binding.
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.
- 17d ago Changed · +23 lines 2dd1dc24b000
- 1mo ago First seen · 55 lines · 92 tokens per session scan A 23f05b894856
visual-verification is a skill published in the GitHub repository HECer/yoke (2 stars, last pushed 8d ago), licensed MIT. It adds 92 tokens to every session and 883 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
qe2etest
Run quick end-to-end smoke testing for {{COMPANYSLUGUPPER}} changes by tracing changed code paths through the real local stack and verifying behavior live.
qmanualt
Perform comprehensive {{COMPANYSLUGUPPER}} acceptance testing with live UI, API, DB, and evidence capture for every acceptance criterion.
qshipcheck
Validates that all orchestrator Phase 2 (review), Phase 3 (acceptance), and Phase 4 (deliver) steps were executed after qship pipeline completion. Run this after qship finishes to catch any skipped steps.
nestjs-testing
NestJS testing best practices (unit and e2e). Use when writing or reviewing NestJS tests — Test.createTestingModule, mocking providers, controller/service unit tests, or e2e with supertest. Triggers on TestingModule, createTestingModule, overrideProvider, or supertest.
qa-ui
Explore a live web application and build a complete ui-test.yaml interaction script for accessibility-cli. Follows the same live-explore workflow as accessibility-cli — writes YAML header first, then resolves real selectors page by page and writes each step the moment it is confirmed. Produces interaction steps only…
qa-codegen
Generate test code, load test configs, and UI automation scripts using the right tool per domain. For API tests uses apigenerator (DQ MCP server). For performance uses dq-nbomber generate + export. For UI/A11y uses a11y-cli playwright-cli exploration. Never generates from scratch — always uses the appropriate tool…