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 fledgeling-co/fledgeling-plugins --skill ui-regressiongit clone --depth 1 https://github.com/fledgeling-co/fledgeling-pluginsWrote 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/fledgeling-co/fledgeling-plugins/ui-regression)<a href="https://agentmods.dev/skills/fledgeling-co/fledgeling-plugins/ui-regression"><img src="https://agentmods.dev/badge/skills/fledgeling-co/fledgeling-plugins/ui-regression/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/fledgeling-co/fledgeling-plugins/ui-regression"><img src="https://agentmods.dev/badge/skills/fledgeling-co/fledgeling-plugins/ui-regression.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 | $0.00053 | $0.00940 |
| Opus 5.5 | $0.00021 | $0.00376 |
| Sonnet 5.5 | $0.00011 | $0.00188 |
| Haiku 4.5 | $0.00005 | $0.00094 |
Grade A, and why
ui-regression 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 28d 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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repeatable UI regression
Keep the named journey and stopping condition. Read the existing project harness
and prior case before creating a parallel suite. This is a focused entry point
to test-campaign:test-campaign, not permission to run a full application audit,
fix unrelated features or publish results. Record target app/build/commit, base
URL or bundle id, account/role, data setup, source requirement, test instrument,
run time and permitted write scope. Past history or a mock cannot verify today's
running product.
Freeze the journey and variants
Create a reusable case with a stable id, starting state, semantic navigation targets, action sequence, expected destination and observable effect at each step. Avoid absolute screen coordinates unless there is no supported alternative; if required, bind them to a fresh screenshot/window geometry and fail on mismatch. An opened tab is not proof its requested destination loaded. Read the route, window or source state after each important transition. Keep setup and cleanup explicit, with test data in a permitted disposable environment.
Use the project's actual theme and compact/wide breakpoints. Record exact widths and how the theme was forced; a screenshot filename does not prove either. Cover the requested light/dark × compact/wide combinations and include keyboard navigation in the cells where responsive layout changes focus or controls. If a cell cannot be reached, report blocked/inconclusive with the reason and keep it in the denominator. Do not claim a sampled set is exhaustive. For a user request that only names one width or theme, preserve that scope rather than expanding it.
Execute with the right instrument
Use the project's browser/e2e harness for web and supported native instrumentation
for desktop. Route native foreground turns through proctor:proctor when available,
and build/suite admission through harbourmaster:harbourmaster where applicable.
Discover actual tool capability before relying on an AX-only instrument for
pixels or a screenshot for keyboard effects. An explicit app safety denial is a
stop for that route; never bypass a com.mitchellh.ghostty denial through another
CUA, shell, AppleScript or capture path. Missing instruments are a named blocker.
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.
- 28d ago First seen · 80 lines · 53 tokens per session scan A 64cd9d58f5fa
ui-regression is a skill published in the GitHub repository fledgeling-co/fledgeling-plugins (2 stars, last pushed today), licensed MIT. It adds 53 tokens to every session and 940 once invoked, about $0.0002 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 2026-10-12.
ui-regression compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| ui-regressionfledgeling-co/fledgeling-plugins | Skill | 2 | today | MIT | A | 53 | Claude Code, Codex |
| create-verification-skillYeachan-Heo/oh-my-claudecode | Skill | 41k | yesterday | MIT | A | 45 | Claude Code |
| verify-omnigentomnigent-ai/omnigent | Skill | 11k | yesterday | Apache-2.0 | A | 100 | Claude Code, Codex |
| test-masterJeffallan/claude-skills | Skill | 12k | 10d ago | MIT | A | 104 | Claude Code |
| eval-dataset-designbojieli/ai-agent-book | Skill | 58k | 1mo ago | Apache-2.0 | A | 138 | Claude Code, Codex |
| dogfoodcallstack/agent-device | Skill | 5.3k | yesterday | MIT | A | 55 | Claude Code |
| cua-driverdavidondrej/skills | Skill | 4.3k | yesterday | MIT | A | 68 | Claude Code, Codex |