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.
curl -O https://raw.githubusercontent.com/Filip-Podstavec/claude-leverage/main/AGENTS.mdgit clone --depth 1 https://github.com/Filip-Podstavec/claude-leverageWrote 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/filip-podstavec/claude-leverage/agents-md)<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>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 | $0.01989 | $0.01989 |
| Opus 5 | $0.00994 | $0.00994 |
| Sonnet 5 | $0.00398 | $0.00398 |
| Haiku 4.5 | $0.00199 | $0.00199 |
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.
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.mdimport inCLAUDE.md. - Codex CLI reads
AGENTS.mdnatively (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:
- Security by default — deterministic shell hooks block secrets, dangerous git operations, and force-push before the model can rationalize past them.
- 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.
- Cross-tool by design — the same
AGENTS.md,SKILL.mdfiles, 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):
- This file (
AGENTS.md) — what this repo is and how to work in it. 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.docs/sessions/— the last 1–3 session logs. Where the previous human + agent left off. Often the highest-leverage orientation per token.docs/conventions.md— repo layout + the full code conventions, when you're about to write code.- The code itself — by following imports from the relevant entrypoint.
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 · 169 lines · 1,989 tokens per session scan A fb911d5c37ac
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.
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.
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.
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).
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).
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.
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.