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/eduardmaghakyan/ipe/claude-mdgit clone --depth 1 https://github.com/EduardMaghakyan/ipeWrote 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/eduardmaghakyan/ipe/claude-md)<a href="https://agentmods.dev/instructions/eduardmaghakyan/ipe/claude-md"><img src="https://agentmods.dev/badge/instructions/eduardmaghakyan/ipe/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 | $0.00952 | $0.00952 |
| Opus 5 | $0.00476 | $0.00476 |
| Sonnet 5 | $0.00190 | $0.00190 |
| Haiku 4.5 | $0.00095 | $0.00095 |
Grade A, and why
ipe 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 — 63 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.
What is IPE
Interactive Plan Editor — a Claude Code hook that intercepts ExitPlanMode, opens a browser-based plan review UI (like a GitHub PR review with inline comments), and sends the user's decision back to Claude Code via stdout.
Commands
bun install # install dependencies
bun run build # build UI then compile self-contained binary → ./ipe
bun run test # unit + integration tests (bun test tests/unit tests/integration)
bun run test:e2e # Playwright browser tests (requires chromium)
bun run test:all # all tests
bun run format # prettier auto-fix
bun run format:check # prettier check only
cd packages/ui && bun run dev # Vite dev server with mock API at localhost:5173
Manual test the binary: printf '{"tool_input":{"plan":"# Test\\n\\nStep 1"},"permission_mode":"default"}' | ./ipe
Architecture
Bun monorepo with two workspaces: packages/* and apps/*.
Build pipeline
packages/uibuilds with Vite +vite-plugin-singlefile→ singleindex.html(all JS/CSS inlined)apps/hook/server/index.tsis compiled withbun build --compile→./ipebinary that embeds the HTML viaimport html from "../ui/dist/index.html" with { type: "text" }
Packages
apps/hook/server/index.ts— Binary entrypoint. Reads Claude Code's JSON from stdin, starts an in-processBun.serveon an ephemeral port (orIPE_PORTif set), opens the browser, awaits the user's decision via an in-process Promise, writes JSON to stdout, exits.packages/server/— HTTP server (Bun.serve), session management, all API routes, SSE broadcasting for the UI, plan version history (history.ts), browser launching (browser.ts), update checking (update.ts).packages/ui/— Svelte 5 frontend.App.svelteorchestrates session state and SSE subscriptions. Components inlib/, pure utilities inutils/.
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 · 63 lines · 952 tokens per session scan A d138d90e39ec
ipe CLAUDE.md is an instructions file published in the GitHub repository EduardMaghakyan/ipe (20 stars, last pushed 3mo ago), licensed MIT. It adds 952 tokens to every session, about $0.0048 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
seektty AGENTS.md
AGENTS.md instructions for Hilbert-beinghappy/seektty: This repository ships one out-of-tree DeepSeek Harness Bundle. Harness remains the only owner of Agent, Session, model, settings, permissions, Profile, plugin, and persistence state.
roamcode AGENTS.md
AGENTS.md instructions for burakgon/roamcode, covering repository instructions for coding agents, public-repository safety, stable release and ota contract, releasing a stable version and ota changes.
amp-acp AGENTS.md
Instructions for tao12345666333/amp-acp, covering agents.md, commands, architecture and code style.
dev-workspace AGENTS.md
Instructions for iwe-org/dev-workspace, covering agent operating manual, start of every session, the operating loop, conventions and iwe basics.
ob-1 AGENTS.md
Instructions for Overbrilliant/ob-1, covering agents.md, project index, stack, commands and key files.
kumo-coding-agent AGENTS.md
Instructions for kumo-ai/kumo-coding-agent: All instructions, routing tables, and rules are in CLAUDE.md. Read that file as the entry point for this agent.