ida-agent-bridge

ida-agent-bridge is a skill for Claude Code from TsingShui/ida-agent-bridge. It costs 66 tokens per session (2,807 once invoked), scanned A, original, MIT.

A bridge for analyzing programs and compiled binaries with IDA, a reverse-engineering tool. It provides short commands and Python scripts for disassembly, finding references, viewing machine-code data, generating pseudocode, and renaming items.

In plain words
What is it for?
Use it to explore functions and strings, inspect how code connects, examine machine instructions, run IDA scripts, and rename or patch analyzed items in .i64 or .so files.
Why use it?
It gives an agent a way to inspect an IDA database or binary without relying on slow full exports. Changes such as renames, comments, and patches can also be synchronized to files.

Skill for Claude Code

Written for Claude Code: ${CLAUDE_SKILL_DIR} variable. Also seen: positional $N argument.

Good fit Use it to explore functions and strings, inspect how code connects, examine machine instructions, run IDA scripts, and rename or patch analyzed items in .i64 or .so files.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/tsingshui/ida-agent-bridge/ida-agent-bridge
Install

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.

Any agent
npx skills add TsingShui/ida-agent-bridge --skill ida-agent-bridge
Clone the repo
git clone --depth 1 https://github.com/TsingShui/ida-agent-bridge

Made for: Claude Code.

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 ida-agent-bridge

README.md
[![agentmods](https://agentmods.dev/badge/skills/tsingshui/ida-agent-bridge/ida-agent-bridge/github.svg)](https://agentmods.dev/skills/tsingshui/ida-agent-bridge/ida-agent-bridge)
Your own site
<a href="https://agentmods.dev/skills/tsingshui/ida-agent-bridge/ida-agent-bridge"><img src="https://agentmods.dev/badge/skills/tsingshui/ida-agent-bridge/ida-agent-bridge/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for ida-agent-bridge

Your own site · 80×15
<a href="https://agentmods.dev/skills/tsingshui/ida-agent-bridge/ida-agent-bridge"><img src="https://agentmods.dev/badge/skills/tsingshui/ida-agent-bridge/ida-agent-bridge.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 66 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,807 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00066 $0.02807
Opus 5 $0.00033 $0.01404
Sonnet 5 $0.00013 $0.00561
Haiku 4.5 $0.00007 $0.00281

Measured 12d ago against content hash 732546e57d19, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

ida-agent-bridge 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 12d 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.

SKILL.md · 258 lines

How it starts

The opening of the file, as written. The whole thing — 258 lines — stays where its author put it; the contents beside it link to each section on GitHub.

IDA Domain API Reference

启动 ida-bridge

首先执行 ps 确认现有进程:

ps -ef | grep ida-bridge | grep -v grep

根据结果判断:

  • 有进程 → 从命令行参数里直接读取文件路径和端口号,跳到步骤 2
  • 无进程 → 询问用户:

    没有发现正在运行的 ida-bridge。请告诉我:

    1. 要分析的文件路径(.i64 / .so
    2. 需要我帮你启动吗?

用户确认启动后:

ida-bridge /path/to/file.i64 <port> --skip-export &
  • 端口默认 13120,如有冲突自选其他端口
  • 默认加 --skip-export,不做全量导出(速度更快)
  • 如果任务明确需要导出(批量分析、读 function_index.tsv 等),先问用户:

    这个任务可能需要导出函数索引,是否启用导出?(首次较慢)

启动后用 !ping 确认就绪。

Agent 只使用短连接模式。 --human-shell 是给人用的交互模式,Agent 不应使用。


工作流

优先级:REPL 指令 → Python 脚本 → 原生 ida_ 模块*

REPL 快捷指令(echo '!cmd' | nc localhost PORT)
      ↓ 指令无法满足(批量操作/复杂逻辑)
Python 脚本(cat script.py | nc localhost PORT)
      ↓ ida-domain 没有封装
原生 ida_* 模块(直接在脚本中调用)

快捷指令

不需要写 Python,直接发单行命令。这是最快的操作方式。

地址和函数名均可互换(0x... 十六进制地址或符号名)。

探索与查询

echo '!afl' | nc localhost <port>                      # 列出所有函数
echo '!afl jni' | nc localhost <port>                  # 搜含 jni 的函数名
echo '!afi main' | nc localhost <port>                 # 函数详情
echo '!iz ssl' | nc localhost <port>                   # 搜含 ssl 的字符串
echo '!axi malloc' | nc localhost <port>               # 导入符号的所有调用点

输出格式:

# !afl — TAB 分隔: 地址  名称  大小(hex)  callers=N
0x11f0	_ossl_fnv1a_hash	0x38	callers=0
0x1228	_ossl_ctype_check	0x28	callers=2

# !afi — 键值对
name:     _ossl_fnv1a_hash
addr:     0x11f0 - 0x1228
size:     0x38 (56)
callers:  0
callees:  0

# !iz — 地址  内容  refs=N  [引用函数]
0x810ee	ossltest  refs=1  [_alpn_select_cb]

# !axi — 地址  引用类型  [所在函数]
0x12f0    CALL_NEAR  [in: _SSL_read]

交叉引用

echo '!axt 0x1234' | nc localhost <port>               # xrefs to 地址
echo '!axf main' | nc localhost <port>                 # xrefs from 函数名

输出格式:

# !axt / !axf — 地址  引用类型  [所在函数]
0x2f020    CALL_NEAR  [in: _ossl_qlog_set_filter]
0x2f064    CALL_NEAR  [in: _ossl_qlog_set_filter]

反汇编与伪代码

echo '!pd 0x1234' | nc localhost <port>                # 从地址反汇编 16 条(默认)
echo '!pd 0x1234 32' | nc localhost <port>             # 反汇编 32 条
echo '!pdf main' | nc localhost <port>                 # 整函数反汇编(带 CFG block 标注)
echo '!pdc 0x1234' | nc localhost <port>               # 伪代码
echo '!pdc 0x1234 -s' | nc localhost <port>            # 过滤变量声明(大函数用)
echo '!mc main' | nc localhost <port>                  # 微码(默认 generated)
echo '!mc main lvars' | nc localhost <port>            # 微码 maturity: generated/preopt/locopt/calls/glbopt1/glbopt2/glbopt3/lvars
echo '!deps main' | nc localhost <port>                # 递归调用链(默认深度 3)
echo '!deps main 5' | nc localhost <port>              # 调用链深度 5

Read the full file on GitHub · 258 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. 12d ago First seen · 258 lines · 66 tokens per session scan A 732546e57d19

Subscribe to this mod's changes

ida-agent-bridge is a skill published in the GitHub repository TsingShui/ida-agent-bridge (110 stars, last pushed 4mo ago), licensed MIT. It adds 66 tokens to every session and 2,807 once invoked, about $0.0003 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 skills, from other repositories

axiom-sre

Expert SRE investigator for incidents and debugging. Uses hypothesis-driven methodology and systematic triage. Can query Axiom observability when available. Use for incident response, root cause analysis, production debugging, or log investigation.

openclaw/clawhub · 48 tokens

sentry-fix-issues

Find and fix issues from Sentry using MCP. Use when asked to fix Sentry errors, debug production issues, investigate exceptions, or resolve bugs reported in Sentry. Methodically analyzes stack traces, breadcrumbs, traces, and context to identify root causes.

openclaw/clawhub · 58 tokens

rubber-duck

Adversarial "rubber duck" review that turns explaining-out-loud into a hallucination check. The main session is the PRESENTER (it did the work — a design doc, investigation, or analysis — and holds the real reasoning) and reconstructs the topic to a LISTENER — a spawned subagent pinned to a DIFFERENT-vendor model that…

kirodotdev/KiroCrew · 161 tokens

convex-performance-audit

Audits Convex performance for reads, subscriptions, write contention, and function limits. Use for slow features, insights findings, OCC conflicts, or read amplification.

openclaw/clawhub · 38 tokens

convex-insights

Query a running Convex app's logs + health in natural language (official MCP): failures, slow/expensive functions, deploy causality — scoped, evidence-backed, with a dashboard deep link.

openclaw/clawhub · 45 tokens

convex-self-heal

Production error → triaged, root-caused, repaired, and certified (tsc + rehearsal + reproduce-then-gone) fix PR for a human to merge — then confirm the error stops recurring. Never auto-merges.

openclaw/clawhub · 52 tokens