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/aleolidev/claude-react-kit/claude-mdgit clone --depth 1 https://github.com/aleolidev/claude-react-kitWhat 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 | $0.00575 | $0.00575 |
| Opus 5 | $0.00287 | $0.00287 |
| Sonnet 5 | $0.00115 | $0.00115 |
| Haiku 4.5 | $0.00057 | $0.00057 |
Grade A, and why
claude-react-kit 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 2d 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.
This is a copy
100% identical to claude-react-kit CLAUDE.md — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
Commands
# Replace these with your project's actual commands
npm run type-check # TypeScript verification
npm run lint # Linting (zero warnings allowed)
npm run test # Run tests
npm run build # Production build
Architecture — MANDATORY
This project follows a layered architecture with strict import boundaries:
app/pages/routes/ → src/features/ → src/shared/ → src/design-system/ → src/core/
↓ ↓ ↓ ↓ ↓
Data fetching Feature UI + Cross-feature UI primitives App infra
Route handling domain logic reusables (tokens, atoms) (auth, net, i18n)
Import rules (NEVER violate):
- Features NEVER import from other features
core/has ZERO business domain awareness- Components NEVER fetch data — they receive it via props
- Pages/routes are the ONLY place for data fetching
See @.claude/rules/architecture.md for full layer definitions.
Component Rules
- Single responsibility: one component = one job
- Target < 100 lines, hard max 200 lines (split into subfolder)
- Functions: max 20 lines, max 3 parameters
- Use guard clauses (early returns) over nested conditionals
Naming Conventions
| Item | Convention | Example |
|---|---|---|
| Component folders | PascalCase | UserProfile/ |
| Infrastructure folders | lowercase/kebab-case | hooks/, shared/services/ |
| Component files | PascalCase.tsx | UserCard.tsx |
| Hook files | camelCase.ts | useUserData.ts |
| Type/const files | camelCase.ts | userTypes.ts |
| Booleans | is/has/can/should prefix |
isLoading, hasError |
| Handlers | handle + Subject + Action |
handleFormSubmit |
TypeScript
- NEVER use
any— use proper types orunknown - Use
interfacefor objects,typefor unions/primitives - Always handle null/undefined explicitly
Before Finishing Any Task
- Run type-check:
npm run type-check - Verify zero new errors introduced
- Confirm no cross-feature imports were added
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.
- 2d ago First seen · 70 lines · 575 tokens per session scan A a1f67dd0b4eb
claude-react-kit CLAUDE.md is an instructions file published in the GitHub repository aleolidev/claude-react-kit (2 stars, last pushed 6mo ago), licensed MIT. It adds 575 tokens to every session, about $0.0029 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to claude-react-kit CLAUDE.md, differing in 0 lines, and is treated as a copy.
Other instructions, from other repositories
own-planner frontend.instructions.md
Instructions for am-space/own-planner, covering frontend instructions, technology, coding rules and change preferences.
harness-engineering CLAUDE.md
Instructions for jrenaldi79/harness-engineering, covering claude.md, project overview, core features, essential commands and testing.
frontend-stack-blueprint CLAUDE.md
Instructions for barrosohub/frontend-stack-blueprint, covering frontend stack blueprint v2.0.0, the stack (use for every project), architecture (mandatory — apply to all code), universal governance protocol (technology-agnostic) and production reliability (mandatory by applicable profile).
archlint CLAUDE.md
Claude Code instructions for MKanhan/archlint, covering archlint-public and venture.
ruledoctor AGENTS.md
Instructions for syf2211/ruledoctor, a project described as: Agent Skill: read CLAUDE.md & project rules before coding. Optional CLI audit + hooks. Claude/Codex/Cursor.
ruledoctor CLAUDE.md
Instructions for syf2211/ruledoctor, covering 项目规则(ruledoctor 自动生成,请按需修改) and 硬性规则.