clawp: Instructions file for Claude Code

CLAUDE.md

clawp CLAUDE.md is an instructions file for Claude Code from ishmum123/clawp. It costs 2,672 tokens per session, scanned A, original, MIT.

Repository instructions for clawp, a small command-line program that sends prompts to Claude or Kimi and prints the answer. It also describes how the program uses tmux, a terminal session manager, and saved conversation transcripts.

In plain words
What is it for?
It is for understanding, modifying, or extending clawp, including its Claude-compatible multi-turn input and Kimi support.
Why use it?
It gives a coding agent the project rules, architecture, and supported command-line behavior needed to work on clawp correctly.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions Claude Code.

This is ishmum123/clawp's own configuration. It tells Claude Code how to work on clawp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything clawp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to ishmum123/clawp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/ishmum123/clawp/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/ishmum123/clawp

Made for: Claude Code.

Wrote 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.

agentmods badge for clawp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/ishmum123/clawp/claude-md.svg)](https://agentmods.dev/instructions/ishmum123/clawp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/ishmum123/clawp/claude-md"><img src="https://agentmods.dev/badge/instructions/ishmum123/clawp/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 2,672 This file is loaded in full into every session.
When invoked 2,672 The same file — it is already loaded in full.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.02672 $0.02672
Opus 5 $0.01336 $0.01336
Sonnet 5 $0.00534 $0.00534
Haiku 4.5 $0.00267 $0.00267

Measured 7d ago against content hash ee8193ceea2f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

clawp CLAUDE.md scanned grade A 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 7d 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.

Asks the agent to reveal its instructionslowSystem prompt leakage

Directions to print, repeat or translate the system prompt extract configuration the operator did not intend to expose.

`clawp` is a subscription-billed drop-in for `claude -p`: `clawp [flags] [prompt]` (or `echo prompt | clawp`) takes a prompt from a positional arg or stdin, prints the answer to stdout, and sends status + the session-id

Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.

CLAUDE.md · 99 lines

How it starts

The opening of the file, as written. The whole thing — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

What this is

clawp is a subscription-billed drop-in for claude -p: clawp [flags] [prompt] (or echo prompt | clawp) takes a prompt from a positional arg or stdin, prints the answer to stdout, and sends status + the session-id to stderr with proper exit codes. Single file (clawp.py), Python standard library only.

Why it exists: scripted use of the interactive TUI bills against the Claude subscription, while claude -p draws from the Agent SDK credit pool. clawp must therefore never call claude -p. It runs the interactive TUI in an ephemeral tmux pane and reads the answer back from the transcript jsonl claude writes to disk.

Architecture

clawp "prompt"
  │  client = get_client(--client)  # claude (default) or kimi
  │  session-id = uuid (or --resume <id>; discovered for kimi fresh sessions)
  ├─ session_lock (flock /tmp/clawp-<name>.lock, one turn/pane)
  ├─ ensure_session ── tmux new-session "<client> <backend-specific launch args>"
  │                    clears trust prompt (Enter) + bypass warning (--full-auto) for claude;
  │                    for kimi, discovers the generated session-id from the welcome screen/index
  │                    waits for idle
  ├─ offset = len(read_records(transcript))   # before send; swallows prior turn's tail
  ├─ send_text ── prompt VERBATIM via bracketed paste
  ├─ capture loop (POLL=0.6s) — DUAL SIGNAL completion:
  │     transcript: terminal record per client adapter ─> capture answer text
  │     screen backstop: idle prompt + no spinner + stable    ─> done (unknown future stop_reason)
  │     blocked (permission/trust dialog)  ─> exit 3
  │     stall / MAX_TURN                    ─> exit 4
  └─ _log_turn → INSERT into responses (sqlite) ── kill pane (every exit path)

Transcript path is deterministic from the session-id: ~/.claude/projects/*/<session-id>.jsonl. Spinner = an ellipsis () on a non-box line in the bottom region (the launch "What's new" box also uses , so boxed lines don't count); idle = any IDLE_MARKERS substring in the status bar (Model: / shift+tab / /effort — the bar text varies by version/plan) and no dialog markers. Schema-break fallback: settled but zero parsed answer → text mode falls back to lossy scrape_reply (flagged low_fidelity); json/stream-json loud-fail.

Read the full file on GitHub · 99 lines

Changes

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.

  1. 7d ago First seen · 99 lines · 2,672 tokens per session scan A ee8193ceea2f

Subscribe to this mod's changes

clawp CLAUDE.md is an instructions file published in the GitHub repository ishmum123/clawp (5 stars, last pushed 1mo ago), licensed MIT. It adds 2,672 tokens to every session, about $0.0134 per session on Opus 5. A static security scan graded it A with 1 finding (asks the agent to reveal its instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other instructions, from other repositories

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.

openai/codex · 5,182 tokens

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).

microsoft/vscode · 6,785 tokens

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.

vercel/next.js · 7,296 tokens

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.

langchain-ai/langchain · 4,469 tokens

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).

microsoft/vscode · 5,001 tokens

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.

github/spec-kit · 7,104 tokens