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 joi-fairshare/agentic-workflow --skill ui-evidencegit clone --depth 1 https://github.com/joi-fairshare/agentic-workflowWrote 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/joi-fairshare/agentic-workflow/ui-evidence)<a href="https://agentmods.dev/skills/joi-fairshare/agentic-workflow/ui-evidence"><img src="https://agentmods.dev/badge/skills/joi-fairshare/agentic-workflow/ui-evidence/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/joi-fairshare/agentic-workflow/ui-evidence"><img src="https://agentmods.dev/badge/skills/joi-fairshare/agentic-workflow/ui-evidence.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 | $0.00063 | $0.02992 |
| Opus 5.5 | $0.00025 | $0.01197 |
| Sonnet 5.5 | $0.00013 | $0.00598 |
| Haiku 4.5 | $0.00006 | $0.00299 |
Grade A, and why
ui-evidence scanned grade A with 1 finding 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 15d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- **Per image, one at a time** (the signed URL lives 60s): `mcp: linear/prepare_attachment_upload` (issue, filename, contentType `image/png`, exact size) → PUT the bytes with every returned header verbatim (`buildPutComm The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
What ships with it
60 files 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.
- .gitignore 43 B
- examples/design-parity/example-manifest.json 1.8 KB
- examples/design-parity/example-parity.json 3.5 KB
- examples/design-parity/example-side-by-side.png 233 KB
- package-lock.json 79 KB
- package.json 671 B
- scripts/doctor.sh 1.7 KB runs code
- scripts/lib/locks.sh 1.6 KB runs code
- scripts/lib/tests/doctor.test.sh 4.1 KB runs code
- scripts/lib/tests/locks.test.sh 1.9 KB runs code
- src/bin.ts 692 B runs code
- src/cli.ts 3.8 KB runs code
- src/db-provenance.ts 2.4 KB runs code
- src/expected-state.ts 1.9 KB runs code
- src/host-guard.ts 6.1 KB runs code
- src/judge-exec.ts 1.1 KB runs code
- src/lint-page.ts 4.6 KB runs code
- src/parity-cli.ts 4.8 KB runs code
- src/parity-publish.ts 5.3 KB runs code
- src/parity-run.ts 9.2 KB runs code
- src/parity-schema.ts 4.2 KB runs code
- src/parity.ts 7.6 KB runs code
- src/pixel-diff.ts 2.9 KB runs code
- src/pixelmatch.d.ts 337 B runs code
- src/publish.ts 5.7 KB runs code
- src/repair.ts 1.2 KB runs code
- src/run-script.ts 7.8 KB runs code
- src/script-schema.ts 2.4 KB runs code
- src/step-exec.ts 4.3 KB runs code
- src/usage.ts 874 B runs code
- src/user-agent.ts 661 B runs code
- src/verdict-cache.ts 2.3 KB runs code
- src/visual-critique.ts 1.3 KB runs code
- src/visual-gate.ts 3.2 KB runs code
- tests/browser/fixture.ts 1.2 KB runs code
- tests/browser/parity-run.browser.test.ts 11 KB runs code
- tests/browser/run-script.browser.test.ts 4.8 KB runs code
- tests/browser/step-exec.browser.test.ts 7.6 KB runs code
- tests/cli.test.ts 5.3 KB runs code
- tests/db-provenance.test.ts 3.7 KB runs code
- tests/expected-state.test.ts 2.5 KB runs code
- tests/host-guard.test.ts 7.1 KB runs code
- tests/judge-exec.test.ts 2.0 KB runs code
- tests/lint-page.test.ts 6.5 KB runs code
- tests/parity-cli.test.ts 7.3 KB runs code
- tests/parity-example.test.ts 2.1 KB runs code
- tests/parity-publish.test.ts 5.9 KB runs code
- tests/parity-schema.test.ts 3.3 KB runs code
- tests/parity.test.ts 7.2 KB runs code
- tests/pixel-diff.test.ts 2.7 KB runs code
- tests/publish-artifacts.test.ts 3.7 KB runs code
- tests/publish.test.ts 6.6 KB runs code
- tests/repair.test.ts 1.5 KB runs code
- tests/script-schema.test.ts 2.3 KB runs code
- tests/usage.test.ts 1.0 KB runs code
- tests/user-agent.test.ts 782 B runs code
- tests/verdict-cache.test.ts 2.6 KB runs code
- tests/visual-critique.test.ts 2.1 KB runs code
- tests/visual-gate.test.ts 5.6 KB runs code
- tsconfig.json 459 B
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.
- 15d ago Changed · +31 lines 4692a80a3e1f
- 21d ago Changed · +11 lines d68faa2dfaeb
- 22d ago Changed c85391b33d7e
- 23d ago First seen · 30 lines · 63 tokens per session scan A c0a278eb0a8d
ui-evidence is a skill published in the GitHub repository joi-fairshare/agentic-workflow (4 stars, last pushed 12d ago), with no licence file. It adds 63 tokens to every session and 2,992 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-28.
Other skills, from other repositories
browse
Drive a real browser through Aside: open a page, read it, click through a flow, take screenshots, check console errors. (gstack).
cua-driver
Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling, calendar entry, screenshots, and demo recording. Also covers Cua setup; not OpenAI Codex Computer Use or web research.
create-verification-skill
Create a repo-local verification skill and exhaustive feature map for driving a real app through its UI, CLI, or API. Use for "create a verification skill", "make a verify skill for this repo", or "document how agents can verify this app".
browser-qa
A browser-based quality check for deployed web pages and user flows. It uses browser automation to test rendering, navigation, forms, interactions, responsive behaviour, and accessibility-related issues.
webapp-testing
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
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…