FuckClaude is a bilingual web tool that checks browser-visible signals and estimates whether Claude Code might identify the environment as belonging to a China-based user. It is for people who want to inspect signals such as the system timezone and proxy hostname without sending data over the network, since the scan runs locally. The catalogue rule and skill provide agent-oriented guidance related to the tool.
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/LinXiaoTao/FuckClaudeWrote 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/rules/linxiaotao/fuckclaude/project-conventions)<a href="https://agentmods.dev/rules/linxiaotao/fuckclaude/project-conventions"><img src="https://agentmods.dev/badge/rules/linxiaotao/fuckclaude/project-conventions/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/rules/linxiaotao/fuckclaude/project-conventions"><img src="https://agentmods.dev/badge/rules/linxiaotao/fuckclaude/project-conventions.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 | $0.01416 | $0.01416 |
| Opus 5.5 | $0.00566 | $0.00566 |
| Sonnet 5.5 | $0.00283 | $0.00283 |
| Haiku 4.5 | $0.00142 | $0.00142 |
Grade A, and why
project-conventions 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 19d 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 — 44 lines — stays where its author put it; the contents beside it link to each section on GitHub.
FuckClaude Project Conventions
Tech Stack & Architecture
- Framework: Astro (SSG/SSR hybrid via
@astrojs/vercel) + TypeScript. - Production Domain:
https://fuck-claude.vercel.app(canonical). Custom domains (fuckclaude.tech,www.fuckclaude.tech) 308 redirect to this origin. - Styling: Scoped CSS using site-wide CSS variables (
var(--surface),var(--border),var(--accent),var(--mono), etc.). - Mobile header: The shared
.nav/.nav__actions/.brand__textstyles live insrc/layouts/BaseLayout.astro. Atmax-width: 560pxthe brand collapses to the logo and.nav__actionswraps onto a second row. New header items must not break this; verifydocumentElement.scrollWidth === viewport widthat 320/360/375/414px on/,/zh/,/guides/,/news/. - Grids and long tokens: Use
minmax(min(Npx, 100%), 1fr)forauto-fillgrids, andoverflow-wrap: anywhereon cards that render user-facing text with long identifiers (env vars, model names).
Bilingual & i18n
- Supported languages:
zh(paths prefixed with/zh/) anden(paths at/). - All user-facing strings must be defined in
src/i18n/ui.tsfor both languages. - Breadcrumbs, alternate hreflang links, and JSON-LD must stay in sync across
/zh/and root versions. - Automatic client/server redirects based on browser language are strictly forbidden per Google SEO guidelines.
- Use
src/components/LocaleSuggestBanner.astroto render a non-blocking suggestion banner when browser language differs from current page language.
News & Community Content
- News: Maintained in
src/config/news.ts. Items include bilingual title, summary, takeaway, category tag, and source link.publishedAtmust match the date on the cited source page (for example the Transparency Hub's "Last updated" date), not the date the item was added. - Non-official news items (media or community reports, such as regional ban waves): cite the original publisher in
sourceName, cross-check at least two independent sources, and state that Anthropic has not confirmed causes or scale. Do not cite vendor blogs that sell a competing service as the sole source. - Social / X Community Posts: Maintained in
src/config/community-posts.tsand rendered viasrc/components/CommunityPosts.astro. Must retain direct links to original X posts, author name, handle, profile link, tags, and practical takeaways. Verify each post before adding it (author, date, text) throughhttps://api.fxtwitter.com/<handle>/status/<id>. Never add posts that cannot be verified, and do not repeat advice that tells users to open replacement accounts after a ban. Available tags are defined inPOST_TAGS; each tag also needs adata-tagcolour rule inCommunityPosts.astro. - News filtering:
ClaudeNews.astroandgetLatestNews()acceptcategories; the guides hub shows onlypolicyandsecurityitems, after the guide catalog. - Community post links: Every post in
community-posts.tssetsrelatedGuideSlug;CommunityPosts.astrorenders it as a "Related guide" link.
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.
- 19d ago Changed · +11 lines · +755 tokens per session 9bd38f430dc4
- 28d ago Changed · +2 lines · +162 tokens per session 92a401d0f73e
- 1mo ago Changed · +2 lines · +46 tokens per session e4d4cab55b85
- 1mo ago Changed · +3 lines · +54 tokens per session 74670c54f7a9
- 1mo ago Changed · +1 lines · +43 tokens per session ba786dea7db2
- 1mo ago First seen · 25 lines · 356 tokens per session scan A 1fd1a25ce62f
project-conventions is a cursor rule published in the GitHub repository LinXiaoTao/FuckClaude (1,105 stars, last pushed yesterday), licensed MIT. It adds 1,416 tokens to every session, about $0.0057 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 2026-09-06.
Other cursor rules, from other repositories
slice-tasks
PLANNING SPINE STEP 2 of 3 — Slice the work: break a scoped PRD into vertical-slice stories in specs/epics/. Use after scope-work (step 1), before plan-work (step 3). Not a substitute for scope-work or plan-work.
iris
GitHub operations specialist — branches, pull requests, issues, releases, tags. Called by zeus after review. Never pushes or merges without explicit human approval. Integrates with VS Code GitHub Pull Requests extension.
elite-orchestrator
Elite orchestrator for mission-critical, enterprise-scale tasks requiring strategic coordination of 7+ agents across all domains. Makes architectural decisions, manages risk, ensures business continuity, and delivers enterprise-grade outcomes. Use for platform migrations, security incidents, multi-system integrations…
project-onboarding-rule
Automatically onboards existing projects into the AI-driven development workflow.
linear-in-review
After finishing a Linear issue, set its status to In Review (never Done).
sprint-planning
BMAD BMM Agent: sprint-planning.