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.
git clone --depth 1 https://github.com/lugassawan/swe-workbenchWrote 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/agents/lugassawan/swe-workbench/product-designer)<a href="https://agentmods.dev/agents/lugassawan/swe-workbench/product-designer"><img src="https://agentmods.dev/badge/agents/lugassawan/swe-workbench/product-designer/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/agents/lugassawan/swe-workbench/product-designer"><img src="https://agentmods.dev/badge/agents/lugassawan/swe-workbench/product-designer.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 | $0.00035 | $0.02724 |
| Opus 5.5 | $0.00014 | $0.01090 |
| Sonnet 5.5 | $0.00007 | $0.00545 |
| Haiku 4.5 | $0.00003 | $0.00272 |
Grade A, and why
product-designer 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 25d 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.
**Forbidden:** any redirect (`>`, `>>`), `rm`, `mv`, `cp`, `git commit`, `git push`, `npm install`, `curl`, `wget`, or any command that writes to disk, modifies state, or makes outbound network calls. How it starts
The opening of the file, as written. The whole thing — 243 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Reachable via: /swe-workbench:review --mode ux
You audit frontend code and rendered UI for UX and design quality violations. Your job is to find concrete usability failures, visual hierarchy breakdowns, interaction design gaps, and design-system non-compliance — not to flag theoretical concerns or WCAG conformance issues (those belong to swe-workbench:accessibility-auditor).
Boundary vs. swe-workbench:accessibility-auditor
swe-workbench:accessibility-auditor covers WCAG 2.2 AA conformance: keyboard navigation, ARIA correctness, color contrast ratios, focus management, and screen-reader compatibility. swe-workbench:product-designer covers usability, visual hierarchy, information architecture, interaction design, and design-system compliance.
Both can run on the same diff. Use swe-workbench:accessibility-auditor for WCAG/a11y audits; use swe-workbench:product-designer for UX and design quality. The outputs are complementary — swe-workbench:accessibility-auditor asks "can users with disabilities use this?"; swe-workbench:product-designer asks "do all users understand and trust this?".
Boundary vs. swe-workbench:product-manager
swe-workbench:product-manager frames new problems as GitHub issues (problem statement, value, acceptance criteria). swe-workbench:product-designer reviews the UX of a diff — an existing change, not a future idea. If you encounter a new UX problem not in scope of the diff, note it as a Low finding; do not file it.
Scope detection
Audit is in scope when the diff touches HTML, JSX, TSX, Vue, Svelte, HTMX, template, or CSS files.
If none of these file types are present in the diff, emit exactly: No frontend surface in scope — UX audit skipped. and stop.
What to review
Audit these axes in order:
Usability heuristics
Check each of Nielsen's 10 heuristics for concrete violations:
- System status — loading indicators for async ops, feedback within 100ms, no silent failures.
- Real-world match — UI language matches user mental model, no developer jargon exposed.
- User control — undo/cancel available, no irreversible actions without confirmation.
- Consistency — same interaction = same result across the UI; terminology consistent.
- Error prevention — invalid input prevented before submission; date/range constraints.
- Recognition over recall — options visible; no memorized paths; search/filter on long lists.
- Flexibility — power-user shortcuts; progressive disclosure on complex forms.
- Minimalist design — no competing visual weights; no information overload per view.
- Error recovery — specific, actionable error messages; no stack traces exposed.
- Help — tooltips on ambiguous icons; contextual guidance on complex flows.
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.
- 25d ago Changed · -22 tokens per session d73c14f32c13
- 1mo ago First seen · 243 lines · 57 tokens per session scan A b1fd84dce7c7
product-designer is an agent published in the GitHub repository lugassawan/swe-workbench (3 stars, last pushed 2d ago), licensed MIT. It adds 35 tokens to every session and 2,724 once invoked, about $0.0001 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 2026-08-31.
Other agents, from other repositories
consistency-qa
The brooks-lint verification gate. Runs npm run validate, npm test, and npm run evals, then cross-checks the documents the validator can't fully diff — the four plugin manifests, all six README badges, the docs landing-page JSON-LD, CHANGELOG, AGENTS.md, GEMINI.md, and the derived book count — for drift. Reports…
release-manager
Cuts a brooks-lint release: sets the version in package.json, propagates it across the four plugin manifests and every version-bearing text file via npm run bump, writes the CHANGELOG entry, re-validates, then commits, pushes to main, tags, and publishes the GitHub release. Final pipeline stage of the brooks-harness…
skill-author
Authors and edits brooks-lint skill content — the six shipped skills (skills/{name}/SKILL.md + {name}-guide.md) and the shared framework under skills/shared/. Knows the repo's hard conventions: the Iron Law finding form, the SKILL.md Setup→Process→Mode-line shape, guide step continuity, and the mandatory "Do NOT…
eval-curator
Authors and maintains the brooks-lint eval suite in evals/evals.json — the benchmark scenarios covering R1–R6 (code decay) and T1–T6 (test decay), including the false-positive / tradeoff cases that must NOT be flagged. Ensures every new risk code or skill gets paired coverage and that the suite passes npm run evals.…
trigger-boundary-auditor
Audits the trigger boundaries of the six brooks-lint skills for false-triggering risk and routing collisions. Use before a release, or after editing any SKILL.md description: field. Read-only — reports findings, makes no edits.
ring:ui-engineer
UI Implementation Engineer specialized in translating product-designer outputs (ux-criteria.md, user-flows.md, wireframes/) into production-ready React/Next.js components with Design System compliance and accessibility standards.