preloop CLAUDE.md

Repository instructions for preloop, an open-source control system for AI agents that handles tool access, model budgets, approvals, monitoring, and audit records.

In plain words
What is it for?
Use them when working on preloop code, its build or test process, its documentation, or its agent-control features.
Why use it?
They tell a coding agent how to follow the repository's required commands and workflow when changing preloop.

Instructions file

Install

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.

agentmods
npx agentmods add instructions/preloop/preloop/claude-md
Clone the repo
git clone --depth 1 https://github.com/preloop/preloop
Per session 3 This file is loaded in full into every session.
When invoked 3 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin 100% copy Near-identical to another mod 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 $0.00003 $0.00003
Opus 5 $0.00002 $0.00002
Sonnet 5 $0.00001 $0.00001
Haiku 4.5 $0.00000 $0.00000

Measured 2d ago against content hash a54ff182c7e8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

preloop 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.

Origin

This is a copy

100% identical to deepseek-harness 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.

CLAUDE.md · 1 lines

What it actually says

AGENTS.md

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. 2d ago First seen · 1 lines · 3 tokens per session scan A a54ff182c7e8

Subscribe to this mod's changes

preloop CLAUDE.md is an instructions file published in the GitHub repository preloop/preloop (56 stars, last pushed 2d ago), licensed Apache-2.0. It adds 3 tokens to every session, about $0.0000 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to deepseek-harness CLAUDE.md, differing in 0 lines, and is treated as a copy.

Related

Other instructions, from other repositories

arc-relay AGENTS.md

Instructions for comma-compliance/arc-relay, covering arc relay - ai contributor guide, what is arc relay?, project structure, building and testing and server (requires gcc, libsqlite3-dev).

comma-compliance/arc-relay · 1,305 tokens

arc-relay copilot-instructions.md

Instructions for comma-compliance/arc-relay, covering arc relay - ai assistant context, project structure, building and key patterns.

comma-compliance/arc-relay · 367 tokens

agentfootprint AGENTS.md

Instructions for footprintjs/agentfootprint, covering agentfootprint — agent instructions (openai codex), core thesis, the mental model — three slots, six flavors, mock-first development (recommended workflow) and public api.

footprintjs/agentfootprint · 7,987 tokens

awaithumans-human-in-the-loop-ai-agents CLAUDE.md

Instructions for awaithumans/awaithumans-human-in-the-loop-ai-agents, covering awaithumans — codebase guide, what this project is, architecture overview, monorepo structure and package dependency rules.

awaithumans/awaithumans-human-in-the-loop-ai-agents · 4,501 tokens

agentfootprint CLAUDE.md

Instructions for footprintjs/agentfootprint, covering agentfootprint — feature-work map, before you design it: it may already exist, module map, core state & flow and extension points.

footprintjs/agentfootprint · 21,166 tokens

agentweaver copilot-instructions.md

Instructions for sabbour/agentweaver: You are working in Agentweaver, a repo developed with Squad (a named AI agent team) that welcomes contributions from AI agents, including GitHub's @copilot. If you are an AI agent landing here cold, read these entry points before making changes.

sabbour/agentweaver · 348 tokens