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 agentmods add instructions/chafan-dev/chafan-pwa/claude-mdgit clone --depth 1 https://github.com/chafan-dev/chafan-pwaWrote 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/instructions/chafan-dev/chafan-pwa/claude-md)<a href="https://agentmods.dev/instructions/chafan-dev/chafan-pwa/claude-md"><img src="https://agentmods.dev/badge/instructions/chafan-dev/chafan-pwa/claude-md.svg" alt="Measured on agentmods" 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 | $0.01250 | $0.01250 |
| Opus 5 | $0.00625 | $0.00625 |
| Sonnet 5 | $0.00250 | $0.00250 |
| Haiku 4.5 | $0.00125 | $0.00125 |
Grade A, and why
chafan-pwa CLAUDE.md 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 6d 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.
Chafan PWA
Frontend-only SPA for a Chinese-language social Q&A site. The API is a separate service.
Stack: Vue 3 (<script setup>) · Vuetify 3 · Pinia · Vue Router 4 · Vite · TypeScript · Vitest (tests/unit/) · Playwright (e2e/)
Layout: src/views/ pages · src/components/ · src/stores/ (Pinia: main, ui, notifications) · src/composables/ (useAuth, useResponsive, useTheme, …) · src/styles/ (app.scss, variables.scss) · src/api/ + src/api.ts
Branches & deploys
| ref | deploys to |
|---|---|
master (tracks public/master) |
— canonical source of truth |
deploy/preview |
preview.cha.fan |
deploy/master |
cha.fan (production) |
deploy/dev |
dev.cha.fan |
public remote = canonical GitHub repo, where PRs land. deploy remote = the fork Cloudflare Pages builds. Promotion is a manual fast-forward: public/master → deploy/preview → deploy/master, via scripts/deploy-preview.sh / scripts/deploy-prod.sh.
scripts/deploy-preview.sh # fetches public, pushes public/master -> deploy/preview
# then wait a few minutes for Cloudflare to build preview.cha.fan
scripts/deploy-prod.sh # deploy/preview -> deploy/master, with confirmation + rollback tag
- The scripts push the source ref's SHA straight to the deploy remote. Deploying does not go through any local branch — don't merge into a local
preview/masterfirst. The localpreviewbranch is a vestige of the migration; it is not part of the deploy path. git pushhas no--ff-onlyflag — a plain push already refuses non-fast-forwards. Never add it.- Production still serves the pre-migration Vue 2 build, so cha.fan is the visual reference: this tree must match its layout and behavior. That parity is the standing goal.
Migration hazards (read this before debugging any layout bug)
The Vue 2→3 / Vuetify 2→3 migration was largely a mechanical rewrite, so Vuetify 2 spellings that Vuetify 3 renamed still linger. They fail silently — no error, no warning, just wrong layout. If a layout bug has no JS error, suspect a dead class or prop before anything else. Confirm against node_modules/vuetify/dist/vuetify.css.
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.
- 6d ago First seen · 75 lines · 1,250 tokens per session scan A 209967277972
chafan-pwa CLAUDE.md is an instructions file published in the GitHub repository chafan-dev/chafan-pwa (50 stars, last pushed 3d ago), licensed Apache-2.0. It adds 1,250 tokens to every session, about $0.0063 per session on Opus 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 2026-08-30.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.