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/bkerler/ida_rpc/agents-mdgit clone --depth 1 https://github.com/bkerler/ida_rpcWrote 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/bkerler/ida_rpc/agents-md)<a href="https://agentmods.dev/instructions/bkerler/ida_rpc/agents-md"><img src="https://agentmods.dev/badge/instructions/bkerler/ida_rpc/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 | $0.03889 | $0.03889 |
| Opus 5 | $0.01945 | $0.01945 |
| Sonnet 5 | $0.00778 | $0.00778 |
| Haiku 4.5 | $0.00389 | $0.00389 |
Grade A, and why
ida_rpc 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 5d 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 — 379 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — ida-rpc
Agent-focused guidance for developing and extending the IDA Pro RPC plugin.
Automatic Reverse Engineering Usage
When reversing binaries with IDA Pro, prefer ida-rpc before screen scraping,
manual GUI steps, or ad hoc IDAPython scripts.
Use these stable agent probes first:
ida-rpc capabilities
ida-rpc find-project <binary-or-idb>
ida-rpc list-loaders <binary>
Then use:
ida-rpc open <binary-or-idb> --arch <arch> --detach
ida-rpc open <raw.bin> --arch arm --base 0x8000 --loader raw --detach
ida-rpc open <loader.bin> --arch arm --loader miniloader --detach
ida-rpc status --project <idb>
ida-rpc metadata --project <idb>
ida-rpc functions --project <idb> --limit 50
ida-rpc decompile <function-or-address> --project <idb>
ida-rpc xrefs-to <target> --project <idb>
ida-rpc xrefs-from <target> --project <idb>
ida-rpc rename-function <target> <new_name> --project <idb>
ida-rpc set-comment <address> <comment> --project <idb>
ida-rpc save --project <idb>
All automation commands print human-readable text to stdout by default. Pass
--json (before the subcommand) or set IDA_RPC_JSON=1 for JSON output. Treat
{"ok": false, ...} (JSON mode) or Error: <error>: <message> (human mode) as
a recoverable tool error. Set IDA_RPC_DEBUG=1 only when a traceback is needed.
RPC queries should always be run outside the sandbox.
Project Overview
ida-rpc is a JSON-RPC daemon that runs inside IDA Pro (as a plugin) and exposes reverse-engineering capabilities over a Unix domain socket. It is wire-format compatible with ghidra-rpc.
┌─────────────┐ Unix Socket ┌──────────────────────────────┐
│ LLM agent │ ──── JSON/newline ──→ │ ida-rpc daemon │
│ (via CLI) │ ←── JSON/newline ─── │ (IDA Python plugin + server)│
└─────────────┘ └──────────────────────────────┘
Repository Layout
| Path | Purpose |
|---|---|
ida_rpc_plugin.py |
IDA Pro plugin entry point (loaded by IDA on startup) |
ida_rpc/cli.py |
Click-based CLI (ida-rpc command) |
ida_rpc/client.py |
Unix socket client + error types |
ida_rpc/daemon.py |
Daemon lifecycle (start, stop, restart) |
ida_rpc/session.py |
Session persistence (JSON state files) |
ida_rpc/server/main.py |
JSON-line socket server, handler registry |
ida_rpc/server/context.py |
IdaContext — wraps IDA database, thread-safe dispatch |
ida_rpc/server/tools/ |
One module per command family (see below) |
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.
- 5d ago First seen · 379 lines · 3,889 tokens per session scan A 08a11d0c2b56
ida_rpc AGENTS.md is an instructions file published in the GitHub repository bkerler/ida_rpc (157 stars, last pushed 15d ago), licensed MIT. It adds 3,889 tokens to every session, about $0.0194 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).
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.
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.
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).