claude-leverage: Instructions file for Claude Code

AGENTS.md

claude-leverage AGENTS.md is an instructions file for Claude Code, Codex, OpenCode from Filip-Podstavec/claude-leverage. It costs 1,989 tokens per session, scanned A, original, MIT.

Repository instructions for coding agents working in the claude-leverage project, covering how to read the project guidance and follow its security and maintenance rules.

In plain words
What is it for?
Use it when an agent begins work in this repository to find the required instructions, conventions, and safeguards before editing code.
Why use it?
It gives agents a shared starting point for making changes that remain understandable and safe for future developers and agents.

Instructions file for Claude CodeCodexOpenCode

Written for Claude Code and Codex and OpenCode: PreToolUse hook event, but also the file is AGENTS.md. Also seen: mentions CLAUDE.md; mentions subagents; mentions Claude Code.

This is Filip-Podstavec/claude-leverage's own configuration. It tells Claude Code, Codex and OpenCode how to work on claude-leverage 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 claude-leverage configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Filip-Podstavec/claude-leverage. 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/Filip-Podstavec/claude-leverage/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/Filip-Podstavec/claude-leverage

Made for: Claude Code, Codex, OpenCode.

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 claude-leverage AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/filip-podstavec/claude-leverage/agents-md.svg)](https://agentmods.dev/instructions/filip-podstavec/claude-leverage/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/filip-podstavec/claude-leverage/agents-md"><img src="https://agentmods.dev/badge/instructions/filip-podstavec/claude-leverage/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,989 This file is loaded in full into every session.
When invoked 1,989 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.01989 $0.01989
Opus 5 $0.00994 $0.00994
Sonnet 5 $0.00398 $0.00398
Haiku 4.5 $0.00199 $0.00199

Measured 6d ago against content hash fb911d5c37ac, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

claude-leverage AGENTS.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.

AGENTS.md · 169 lines

How it starts

The opening of the file, as written. The whole thing — 169 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Canonical instruction set for any coding agent working in this repo. Read this first, before touching any file.

  • Claude Code loads this via the @AGENTS.md import in CLAUDE.md.
  • Codex CLI reads AGENTS.md natively (no import needed).

Both tools see identical guidance. Tool-specific additions live in CLAUDE.md (below the @AGENTS.md import) — keep them short.

Mission

claude-leverage is Filip Podstavec's personal AI-dev stack for Claude Code and Codex, built to ship secure and long-term-maintainable software for clients when working primarily through AI agents.

The premise: shipping client work with AI agents at velocity is easy; shipping it so the next agent (human or AI) opening the repo in six months can still safely modify it is the hard part. This stack is the guardrails, conventions, and on-demand skills that make the second part automatic — continuously as the repo grows, not just at session start.

Three properties guide every decision here:

  1. Security by default — deterministic shell hooks block secrets, dangerous git operations, and force-push before the model can rationalize past them.
  2. Self-maintaining as the repo grows — non-blocking nudges flag missing AIDEV anchors, missing per-dir AGENTS.md, stale anchors, and review-worthy diffs, so maintenance debt surfaces while it's still cheap to fix.
  3. Cross-tool by design — the same AGENTS.md, SKILL.md files, and hook scripts work in both Claude Code and Codex. Author once.

The point is not to save tokens (that thesis was disproven — see "Honest history" below). It's to make the next agent's job easier than the previous one's, every time.

For what ships in the stack and how it installs, see the README.

Reading order for new agents

Opening this repo for the first time? Read in this order (progressive disclosure: minimum context at session start):

  1. This file (AGENTS.md) — what this repo is and how to work in it.
  2. docs/adr/why the architecture looks the way it does. Skim the index; read the ones relevant to your change. Without these you'll propose refactors away from load-bearing constraints.
  3. docs/sessions/ — the last 1–3 session logs. Where the previous human + agent left off. Often the highest-leverage orientation per token.
  4. docs/conventions.md — repo layout + the full code conventions, when you're about to write code.
  5. The code itself — by following imports from the relevant entrypoint.

Read the full file on GitHub · 169 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. 6d ago First seen · 169 lines · 1,989 tokens per session scan A fb911d5c37ac

Subscribe to this mod's changes

claude-leverage AGENTS.md is an instructions file published in the GitHub repository Filip-Podstavec/claude-leverage (68 stars, last pushed 1mo ago), licensed MIT. It adds 1,989 tokens to every session, about $0.0099 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 2026-08-30.

Related

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.

vercel/next.js · 7,296 tokens

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

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

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

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