Borrowing it
Nothing to install: this file belongs to dhanushkumarsivaji/kerf-cli. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/dhanushkumarsivaji/kerf-cli/main/CLAUDE.mdgit clone --depth 1 https://github.com/dhanushkumarsivaji/kerf-cliWrote 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/dhanushkumarsivaji/kerf-cli/claude-md)<a href="https://agentmods.dev/instructions/dhanushkumarsivaji/kerf-cli/claude-md"><img src="https://agentmods.dev/badge/instructions/dhanushkumarsivaji/kerf-cli/claude-md/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/instructions/dhanushkumarsivaji/kerf-cli/claude-md"><img src="https://agentmods.dev/badge/instructions/dhanushkumarsivaji/kerf-cli/claude-md.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 | $0.00392 | $0.00392 |
| Opus 5 | $0.00196 | $0.00196 |
| Sonnet 5 | $0.00078 | $0.00078 |
| Haiku 4.5 | $0.00039 | $0.00039 |
Grade B, and why
kerf-cli CLAUDE.md scanned grade B 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 8d 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
- Settings: ~/.claude/settings.json (global), .claude/settings.json (project) What it actually says
kerf-cli — Claude Code Cost Intelligence
Project Overview
TypeScript CLI tool providing real-time cost intelligence for Claude Code.
Name origin: kerf = width of material removed by a cutting tool (token waste).
Published as kerf-cli on npm. Distributed via npx kerf-cli@latest. Uses Ink (React for CLI) for terminal UI.
Architecture
- CLI: Commander.js for subcommands, Ink for interactive UI
- Data: Parse JSONL from ~/.claude/projects/, SQLite for budgets
- Hooks: Shell scripts installed to ~/.claude/hooks/
- Token counting: character/3.5 heuristic, Anthropic count_tokens API optional
- Storage: ~/.kerf/kerf.db (SQLite), ~/.kerf/session-log.jsonl
Conventions
- Use Day.js for all date operations (not Moment.js)
- Pin exact versions in package.json (no ^ or ~)
- Use structlog pattern for logging (structured JSON)
- All financial values use string-based precision (avoid floating point)
- ESM modules only (type: module in package.json)
- Prefer named exports over default exports
- Error messages must be actionable (tell user what to do)
Key Paths
- JSONL logs: ~/.claude/projects//.jsonl
- Settings: ~/.claude/settings.json (global), .claude/settings.json (project)
- MCP config: .mcp.json (project), ~/.claude.json (user)
- Hooks: ~/.claude/settings.json hooks[] array
- kerf data: ~/.kerf/kerf.db, ~/.kerf/session-log.jsonl
Testing
- vitest for all tests
- Fixtures in tests/fixtures/
- Mock JSONL data for parser tests
Build
- tsup bundles to dist/
- npm prepublishOnly runs build
- Target: Node 20+
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.
- 8d ago First seen · 40 lines · 392 tokens per session scan B b16d58af9157
kerf-cli CLAUDE.md is an instructions file published in the GitHub repository dhanushkumarsivaji/kerf-cli (5 stars, last pushed 3mo ago), licensed MIT. It adds 392 tokens to every session, about $0.0020 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
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.
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 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).
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).
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.
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.