agentmods.dev

leashd: Instructions file for Claude Code

CLAUDE.md

leashd CLAUDE.md is an instructions file for Claude Code from vmehera123/leashd. It costs 1,144 tokens per session, scanned A, original, Apache-2.0.

A repository instruction file for leashd, a Python project with a web interface, tests, and command-line tools. It documents commands for setup, testing, formatting, type checking, and browser-based checks.

In plain words
What is it for?
It helps install dependencies, run selected or complete tests, measure coverage, lint and format code, check types, and run end-to-end browser tests.
Why use it?
It gives contributors a repeatable verification routine, including checks that catch code errors and failures in the web interface.

Instructions file for Claude Code

Written for Claude Code: PreToolUse hook event. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions Claude Code.

This is vmehera123/leashd's own configuration. It tells Claude Code how to work on leashd 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 leashd configures →

not rated 5repo changed 26d ago A scan 1,144 tokens original Apache-2.0
View source ↗ vmehera123/leashd pypi.org
Reuse

Borrowing it

Nothing to install: this file belongs to vmehera123/leashd. 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/vmehera123/leashd/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/vmehera123/leashd

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 leashd CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/vmehera123/leashd/claude-md/github.svg)](https://agentmods.dev/instructions/vmehera123/leashd/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/vmehera123/leashd/claude-md"><img src="https://agentmods.dev/badge/instructions/vmehera123/leashd/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.

agentmods 80×15 button for leashd CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/vmehera123/leashd/claude-md"><img src="https://agentmods.dev/badge/instructions/vmehera123/leashd/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,144 This file is loaded in full into every session.
When invoked 1,144 The same file — it is already loaded in full.
Security scan A 0 findings. 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 $0.01144 $0.01144
Opus 5.5 $0.00458 $0.00458
Sonnet 5.5 $0.00229 $0.00229
Haiku 4.5 $0.00114 $0.00114

Measured 26d ago against content hash 98b47bb54558, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

leashd 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 26d 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.

CLAUDE.md · 48 lines

How it starts

The opening of the file, as written. The whole thing — 48 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.

leashd is a daemon that runs Claude Code in tmux panes and puts a Sandbox → Policy → Approval pipeline in front of every tool call, driven from a Web UI or Telegram. Product overview: README.md. Subsystem docs: docs/index.md.

Commands

make check          # ruff fix + format, mypy, unit tests
make check-all      # make check + Playwright E2E (tests/e2e/)
uv run pytest -m e2e -v                                    # E2E only; one-time: uv run playwright install chromium
  • Always run through uv run, never bare python / python3.
  • pytest's addopts deselects e2e, so plain uv run pytest never runs the browser tests.
  • IMPORTANT: never pass -q to pytest. addopts already has it, and a second one (-qq) removes the N passed in Xs line, so the run looks like it printed no result. -p no:warnings doesn't bring the line back.
  • The full suite takes about 4 minutes, and make check already runs it, so run it once per verification and never rerun it just to read the result. Send the output to a file in the scratchpad (make check > <scratchpad>/check.log 2>&1; echo "exit=$?") and grep the file as often as you need. Exit 0 means the tests passed.
  • The summary line reads 7830 passed, 65 deselected, 21 warnings in 222s, so a grep -v warning filter deletes it. Match passed|failed instead.
  • While iterating, run only the test files you touched (uv run pytest tests/agents/test_tmux_session.py -k name), and keep the full suite for the final make check.
  • The Makefile runs mypy with || true, so a green make check can hide type errors. Read mypy's output and fix what it reports.
  • CLI surface: leashd --help, leashd <subcommand> --help.

Workflow

  • IMPORTANT: run make check after any implementation work and fix every issue before calling the task done. Also run the E2E tier when you touch the Web UI or browser automation.
  • After each change, add one line to CHANGELOG.md under the current (latest) version heading, as - **added|fixed|changed|removed**: short description. Never create a new version heading.

Read the full file on GitHub · 48 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. 26d ago Changed · +5 lines · +274 tokens per session 98b47bb54558
  2. 28d ago Changed · -56 lines · -925 tokens per session 15a6b0cc39b2
  3. 1mo ago Changed · +3 tokens per session 72f0c98125d8
  4. 1mo ago Changed · -3 lines · -34 tokens per session 8e65066bf8a8
  5. 2mo ago First seen · 102 lines · 1,826 tokens per session scan A 2a7603e076a1

Subscribe to this mod's changes

leashd CLAUDE.md is an instructions file published in the GitHub repository vmehera123/leashd (5 stars, last pushed 7d ago), licensed Apache-2.0. It adds 1,144 tokens to every session, about $0.0046 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 2026-08-31.

AI Safetyagentic-codingai-agentsai-governanceaudit-trailautomation
Related

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).

microsoft/vscode · 9,715 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 · 7,461 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, cache eligibility and rollout and applying the notice (cutover).

microsoft/vscode · 5,262 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 · 4,680 tokens

vscode copilot-instructions.md

Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).

microsoft/vscode · 2,750 tokens

deno copilot-instructions.md

Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.

denoland/deno · 3,077 tokens