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 skills add TsingShui/ida-agent-bridge --skill ida-agent-bridgegit clone --depth 1 https://github.com/TsingShui/ida-agent-bridgeWrote 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/skills/tsingshui/ida-agent-bridge/ida-agent-bridge)<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.
<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>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 | $0.00066 | $0.02807 |
| Opus 5.5 | $0.00026 | $0.01123 |
| Sonnet 5.5 | $0.00013 | $0.00561 |
| Haiku 4.5 | $0.00007 | $0.00281 |
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 2mo 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 — 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:
- 要分析的文件路径(
.i64/.so) - 需要我帮你启动吗?
- 要分析的文件路径(
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
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.
- 2mo ago First seen · 258 lines · 66 tokens per session scan A 732546e57d19
ida-agent-bridge is a skill published in the GitHub repository TsingShui/ida-agent-bridge (109 stars, last pushed 5mo ago), licensed MIT. It adds 66 tokens to every session and 2,807 once invoked, about $0.0003 per session on Opus 5.5. 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.
ida-agent-bridge compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| ida-agent-bridgeTsingShui/ida-agent-bridge | Skill | 109 | 5mo ago | MIT | A | 66 | Claude Code |
| axiom-sreopenclaw/clawhub | Skill | 9.5k | yesterday | MIT | A | 48 | Claude Code, Codex |
| sentry-fix-issuesopenclaw/clawhub | Skill | 9.5k | yesterday | MIT | A | 58 | Claude Code |
| orca-replayiflytek/skillhub | Skill | 5.4k | yesterday | Apache-2.0 | A | 43 | Claude Code, Codex |
| rubber-duckkirodotdev/KiroCrew | Skill | 4.8k | yesterday | Apache-2.0 | A | 161 | Claude Code, Codex |
| clawhub-clawscanopenclaw/clawhub | Skill | 9.5k | yesterday | MIT | A | 46 | Claude Code, Codex |
| convex-performance-auditopenclaw/clawhub | Skill | 9.5k | yesterday | MIT | A | 38 | Codex |