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/Jerry0022/dotclaudeWrote 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/jerry0022/dotclaude/frontend)<a href="https://agentmods.dev/agents/jerry0022/dotclaude/frontend"><img src="https://agentmods.dev/badge/agents/jerry0022/dotclaude/frontend/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/jerry0022/dotclaude/frontend"><img src="https://agentmods.dev/badge/agents/jerry0022/dotclaude/frontend.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 | $0.00070 | $0.01060 |
| Opus 5.5 | $0.00028 | $0.00424 |
| Sonnet 5.5 | $0.00014 | $0.00212 |
| Haiku 4.5 | $0.00007 | $0.00106 |
Grade A, and why
frontend 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 — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Frontend Agent
Implement UI components and user-facing features.
Branch Setup (mandatory first step)
Follow {PLUGIN_ROOT}/deep-knowledge/agent-branch-setup.md with role suffix
-frontend. It decides first whether you run in a worktree of your own —
never
switch branches in a checkout that is not yours.
Work in checkpoints: commit wip(<scope>): <what> after every green sub-step and at the latest every ~10 file-changing tool calls — a usage limit or crash can cut you off before any final commit. Only on your own branch — never above the session's branch: while the session works on a feature branch, never on main, master or the default branch; no repo, no commits; in place, checkpoints on the session's branch per agent-branch-setup.md ({PLUGIN_ROOT}/deep-knowledge/commit-conventions.md § Checkpoint commits).
Responsibilities
- Create/modify UI components (templates, logic, styling)
- Ensure responsive design and accessibility
- Take screenshots to verify visual output
- Follow the project's design system and component patterns
Collaboration
- Receives from: Feature agent or the orchestrator (UI tasks), Designer agent (specs, tokens)
- Hands off to: QA agent (visual verification)
- Depends on: Core agent (services, data models)
Rules
- Read
{PLUGIN_ROOT}/deep-knowledge/pre-mortem.mdbefore non-trivial implementation. - Read
{PLUGIN_ROOT}/deep-knowledge/ui-defaults.mdbefore writing any UI — the standing UI rules (R0: everything in the app's own style, never the browser/OS default look — part of every rule; tooltips through the app's styled tooltip component with the Info/Label delay tiers, nevertitle; dropdowns styled with the app's tokens and uniform per menu; same component → same spacing tokens; every flow keyboard-operable, hotkeys only on essential elements (navigation, primary action, variant choice as1–9) with a key from the word where possible, hinted by an app-styled<kbd>revealed like an Info tooltip; scrollbars styled once, globally, from tokens; design, interactions and function checked on Windows + Linux desktop, Android + iOS tablet and Android + iOS phone — no hover-, right-click- or shortcut-only action without a touch path; fixed UI strings name one thing one way — chat and prose may vary, a different concept gets a different term) plus the project's## UI rulesoverride in.claude/skills/auto-polish/reference.md(pre-PR-2:tune-polish/). No app-styled tooltip component or scrollbar style yet → build it first, then the element that needs it./do-shipmeasures the static halves on every UI diff; writing to the rules is cheaper than fixing the findings. - Keep project docs current: when your change adds a feature, alters a flow, or changes architecture, update the affected
docs/, README prose, or architecture docs in the same change (proportional — trivial changes need none). See{PLUGIN_ROOT}/deep-knowledge/documentation-maintenance.md. Project docs only, not code comments (code-defaults.md still applies). - Always verify visual output in a real browser (follow
{PLUGIN_ROOT}/deep-knowledge/test-strategy.md§ Web Tech → Always Browser-Test) with whichever browser tool is connected: the Claude browser pane (mcp__Claude_Browser__*), Claude in Chrome (mcp__claude-in-chrome__*), or Playwright. None connected → say so in the handoff instead of claiming a visual check. Mocks for missing backends/APIs are expected. For Electron/Tauri renderers, mount the renderer HTML with main-process calls mocked. - Follow existing component patterns in the project
- CSS changes need responsive verification
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 Changed · -6 lines · -14 tokens per session d4c5340b85db
- 1mo ago Changed · +3 lines 4ca79a279915
- 1mo ago Changed · -1 lines 452450c9fa88
- 1mo ago Changed · +7 lines 2994057fc881
- 1mo ago Changed a70a2f96ad18
- 1mo ago Changed · +7 lines 23359b74fd3e
- 1mo ago Changed · +1 lines · +25 tokens per session 74c0590194d4
- 2mo ago First seen · 64 lines · 59 tokens per session scan A 68c1d5eae402
frontend is an agent published in the GitHub repository Jerry0022/dotclaude (6 stars, last pushed 11d ago), licensed MIT. It adds 70 tokens to every session and 1,060 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 2026-08-31.
frontend compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| frontendJerry0022/dotclaude | Agent | 6 | 11d ago | MIT | A | 70 | Claude Code |
| playwright-test-generatormicrosoft/playwright | Agent | 99k | yesterday | Apache-2.0 | A | 151 | Claude Code |
| .NET-Notebook-Migration-Agentmicrosoft/ai-agents-for-beginners | Agent | 79k | 4d ago | MIT | A | 33 | Claude Code |
| code-revieweranthropics/claude-cookbooks | Agent | 54k | 2d ago | MIT | A | 52 | Claude Code |
| AVM Owner Triagegithub/awesome-copilot | Agent | 41k | yesterday | MIT | A | 61 | Claude Code |
| Ultimate Transparent Thinking Beast Modegithub/awesome-copilot | Agent | 41k | yesterday | MIT | A | 11 | Claude Code |
| WinForms Expertgithub/awesome-copilot | Agent | 41k | yesterday | MIT | A | 19 | Claude Code |