Borrowing it
Nothing to install: this file belongs to eunomia-bpf/ActPlane. 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/eunomia-bpf/ActPlane/master/CLAUDE.mdgit clone --depth 1 https://github.com/eunomia-bpf/ActPlaneWrote 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/eunomia-bpf/actplane/claude-md)<a href="https://agentmods.dev/instructions/eunomia-bpf/actplane/claude-md"><img src="https://agentmods.dev/badge/instructions/eunomia-bpf/actplane/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 | $0.02201 | $0.02201 |
| Opus 5 | $0.01100 | $0.01100 |
| Sonnet 5 | $0.00440 | $0.00440 |
| Haiku 4.5 | $0.00220 | $0.00220 |
Grade B, and why
ActPlane CLAUDE.md scanned grade B with 1 finding 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
sudo bash script/e2e_examples.sh # live policy match of all 12 examples (E1–E12) How it starts
The opening of the file, as written. The whole thing — 183 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.
Overview
ActPlane is an OS-level harness for AI agents. It compiles a policy DSL
to an in-kernel eBPF engine that performs labeled information-flow control
across process / file / network edges and reports only rule matches —
each with a human-readable reason (the corrective-feedback payload). It applies
policies below the tool layer (at the syscall boundary), so constraints hold across any
tool, subprocess, or direct syscall the agent uses. (The mechanism is a labeled,
runtime form of information-flow control — unlike classic taint analysis, which
is single-bit, usually offline, and aimed at finding vulnerabilities. Code-level
identifiers still use taint — taint.h, taint_config, te_* — as the
implementation name.)
The repo descends from AgentSight (an eBPF observability framework); the SSL/HTTP analyzer chain, runners, web server, and frontend were removed. What remains is the labeled information-flow engine plus a minimal Rust compiler/driver.
Agent behavioral constraints (ActPlane-applied)
When acting as an agent in this repo, do not run git branch or git worktree —
the user does not want new branches or worktrees created right now. Other git
operations are allowed (git commit, git add, git status, git log, git push,
…). If you think a different branch is needed, ask the user instead of creating one.
git branch and git worktree are also applied below the tool layer by ActPlane
itself (actplane.yaml, rule no-git-branch, kill exec "git" "branch"/kill exec "git" "worktree"): they
are killed whether invoked via a tool call, bash -c, or a subprocess — a worked
example of a real corpus-derived guardrail in the taint DSL.
When an operation fails with EPERM / Operation not permitted, or a tool hook
injects an [ActPlane] message, treat it as authoritative kernel feedback. Read
.actplane/last-violation.txt if you need the full reason, then follow the
suggested path instead of retrying the same operation unchanged.
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 · 183 lines · 2,201 tokens per session scan B 66a3ce917f71
ActPlane CLAUDE.md is an instructions file published in the GitHub repository eunomia-bpf/ActPlane (97 stars, last pushed yesterday), licensed MIT. It adds 2,201 tokens to every session, about $0.0110 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). 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.