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 ze-mu-zhou/IDACLI --skill ida-cligit clone --depth 1 https://github.com/ze-mu-zhou/IDACLIWrote 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/ze-mu-zhou/idacli/ida-cli)<a href="https://agentmods.dev/skills/ze-mu-zhou/idacli/ida-cli"><img src="https://agentmods.dev/badge/skills/ze-mu-zhou/idacli/ida-cli/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/ze-mu-zhou/idacli/ida-cli"><img src="https://agentmods.dev/badge/skills/ze-mu-zhou/idacli/ida-cli.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00070 | $0.01558 |
| Opus 5 | $0.00035 | $0.00779 |
| Sonnet 5 | $0.00014 | $0.00312 |
| Haiku 4.5 | $0.00007 | $0.00156 |
Grade A, and why
ida-cli 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 10d 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 — 198 lines — stays where its author put it; the contents beside it link to each section on GitHub.
IDA-CLI
Use the repository that contains pyproject.toml with project name ida-cli.
The runtime is AI-only: one target argument, stdin JSONL requests, stdout JSONL
responses, unrestricted Python execution, persistent globals, and artifact-
backed large outputs.
The supported IDA surface is IDA Pro 9.0+ simple-open idalib workflows. This
skill does not expose the extra loader-argument variants that IDA 9.1/9.2 added
to open_database().
Install Runtime
From the repository root:
cd <IDA_ROOT>\idalib\python
python -m pip install idapro
python py-activate-idalib.py
cd <IDA_CLI_REPO>
python -m pip install -e .
IDA-CLI probes an already importable idapro first. If that official setup was
skipped, the runtime next checks IDADIR and bounded Windows install layouts.
Full-drive discovery is slow and off by default; opt into it with
IDA_CLI_DEEP_IDA_DISCOVERY=1 only as a last resort.
In WSL, AgentSession auto-detects the Windows Python with idapro and converts
paths automatically. Set IDA_CLI_PYTHON to override.
Required Readiness Check
Before opening a real target or starting AgentSession, run:
ida-ai doctor
Proceed only when the JSONL result reports status: "ready" and
license_accepted: true. The result also identifies the active IDA root,
version, .hexlic file, license terms, and idapro configuration file.
If the CLI reports IdaLicenseNotAcceptedError, stop the target startup and
run the explicit one-time repair:
ida-ai doctor --fix-license
That command launches the configured official IDA executable, waits for the user to review and accept Hex-Rays' terms and close IDA, then retries idapro in an isolated subprocess. Never click the acceptance control for the user, write an undocumented acceptance marker, patch licensing files, or silently downgrade to the Python-only backend. Acceptance is per OS user, so service and CI accounts must pass the same readiness check.
For other doctor failures, preserve the structured details object and fix the
reported IDA path, idapro installation, or license-file problem before analysis.
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.
- 10d ago First seen · 198 lines · 70 tokens per session scan A 88cf8d0ec937
ida-cli is a skill published in the GitHub repository ze-mu-zhou/IDACLI (43 stars, last pushed 1mo ago), licensed MIT. It adds 70 tokens to every session and 1,558 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.
Other skills, from other repositories
Reverse Engineering & Binary Analysis
Binary analysis, assembly interpretation, disassembly, decompilation, firmware RE, and protocol reverse engineering.
reverse-engineer-anything
Reverse engineer native, managed, Electron/JavaScript, packaged, and browser applications with REA. Use shipped-artifact or approved runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.
revx-native
Analyze native Android libraries (libil2cpp.so, libGameCore.so, ARM64 .so) with revx — a memory-frugal native reverse-engineering CLI. Find il2cpp method-pointer tables, recover class/field metadata, export offset tables for game tooling, and decompile ARM64 functions. Use when the user wants to analyze native .so…
code_explorer
Explores the repository to locate primary source files, coupled UI components, and test files for bug reports or feature requests.
session-investigator
Investigate fast-agent session and history files to diagnose issues. Use when a session ended unexpectedly, when debugging tool loops, when correlating sub-agent traces with main sessions, or when analyzing conversation flow and timing. Covers session.json metadata, history JSON format, message structure, tool…
smiles-validation
Strict SMILES validation, structural comparison, and modification verification. Catches invalid LLM-generated molecules.