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/vmehera123/leashd/claude-mdgit clone --depth 1 https://github.com/vmehera123/leashdWrote 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/vmehera123/leashd/claude-md)<a href="https://agentmods.dev/instructions/vmehera123/leashd/claude-md"><img src="https://agentmods.dev/badge/instructions/vmehera123/leashd/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 | $0.01826 | $0.01826 |
| Opus 5 | $0.00913 | $0.00913 |
| Sonnet 5 | $0.00365 | $0.00365 |
| Haiku 4.5 | $0.00183 | $0.00183 |
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 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 — 102 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.
See @README.md for project overview. Detailed docs in @docs/index.md.
Commands
# Install dependencies
uv sync
# Run tests (single file / specific test / all)
uv run pytest tests/test_policy.py -v
uv run pytest tests/test_policy.py::test_function_name -v
uv run pytest tests/
# Run tests with coverage
uv run pytest --cov=leashd tests/
# Lint + format
uv run ruff check --fix . && uv run ruff format .
# Type check
uv run mypy leashd/
# Full check (lint + format + mypy + tests) — ALWAYS run after implementation work
make check
# E2E tests (Playwright, real browser vs WebUI) — NOT included in `make check`
uv run playwright install chromium # one-time setup
uv run pytest -m e2e -v
make check-all # = make check + E2E
# JS unit tests (WebUI utils.js, Vitest) — NOT included in `make check`
cd tests/js && npm install && npm test
CLI commands are discoverable via leashd --help and leashd <subcommand> --help.
Specs
Before exploring the codebase, read the relevant spec in specs/app/. Start with specs/app/00-quick-reference.md for the file-to-class map, then consult the numbered spec for whichever subsystem you're working on. These are detailed technical references that save significant exploration time. Always verify spec information against the actual source code — specs can drift from the implementation, so treat them as a starting point, not the source of truth.
Code Exploration
For structural "where does this live / what calls it / what shape is it" questions, reach for codebase-memory-mcp first (a SessionStart hook re-injects its tool list each session, so it isn't repeated here). The graph tells you where; it can lag the working tree, so always Read the file to confirm against disk before you Edit — that validation step is mandatory for any non-trivial change. Skip the graph and go straight to Read/Grep/Glob for non-code files (Markdown, YAML, config) and when you already know the path.
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 · 102 lines · 1,826 tokens per session scan A 2a7603e076a1
leashd CLAUDE.md is an instructions file published in the GitHub repository vmehera123/leashd (5 stars, last pushed 11d ago), licensed Apache-2.0. It adds 1,826 tokens to every session, about $0.0091 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 2026-08-31.
Other instructions, from other repositories
CORE CLAUDE.md
Claude Code instructions for DariuszNewecki/CORE, covering claude.md — core, what core is, and what you are, source layout, how to work in this repo and governed and prohibited surfaces.
martin-loop AGENTS.md
AGENTS.md instructions for Keesan12/martin-loop, covering martinloop agent operating rules, repository authority, mandatory internal-first sequence, prohibited actions and required internal health proof.
orloj AGENTS.md
AGENTS.md instructions for OrlojHQ/orloj, covering orloj agent instructions, must-follow sync rules and working style.
orloj CLAUDE.md
Claude Code instructions for OrlojHQ/orloj, covering orloj claude instructions, critical repository rules and implementation notes.
FylloCode AGENTS.md
AGENTS.md instructions for Fioooooooo/FylloCode, covering agents.md, 项目概述, 技术栈, 目录结构 and 常用命令.
sint-protocol CLAUDE.md
Instructions for sint-ai/sint-protocol, covering sint protocol — agent guide, what is this?, quick commands, monorepo layout and architecture rules.