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 02loveslollipop/OpenCROW --skill opencrow-reversing-toolboxgit clone --depth 1 https://github.com/02loveslollipop/OpenCROWWrote 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/02loveslollipop/opencrow/opencrow-reversing-toolbox)<a href="https://agentmods.dev/skills/02loveslollipop/opencrow/opencrow-reversing-toolbox"><img src="https://agentmods.dev/badge/skills/02loveslollipop/opencrow/opencrow-reversing-toolbox/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/02loveslollipop/opencrow/opencrow-reversing-toolbox"><img src="https://agentmods.dev/badge/skills/02loveslollipop/opencrow/opencrow-reversing-toolbox.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 | $0.00102 | $0.01028 |
| Opus 5 | $0.00051 | $0.00514 |
| Sonnet 5 | $0.00020 | $0.00206 |
| Haiku 4.5 | $0.00010 | $0.00103 |
Grade A, and why
opencrow-reversing-toolbox 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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OpenCROW Reversing Toolbox
Runtime preflight
Probe required commands with command -v and Python modules with importlib.util.find_spec before use. Prefer a PATH-resolved OpenCROW MCP helper or the ctf/sage environment when available, then the managed helper or system Python. If a capability is missing, stop that path safely and report the exact missing command or module.
Prefer the opencrow-reversing-mcp server for typed disassembly, decompilation, VA-based data reads, emulation, symbolic execution, tracing, gadget search, and Python-driven analysis. Fall back to the direct scripts only when you need to debug the underlying ctf-environment execution path.
MCP First
- Use
toolbox_info,toolbox_verify, andtoolbox_capabilitiesfirst. - Use the typed reversing operations:
reversing_pythonreversing_disassemblereversing_decompilereversing_read_datareversing_emulate_blobreversing_symbolic_executereversing_tracereversing_binwalkreversing_gadget_search
- Treat the existing helper scripts as the implementation fallback, not the primary interface.
- For long workflows, pass
execution.transcript_pathso each MCP step appends a JSONL transcript artifact instead of relying on chat history.
Use this skill for understanding binaries rather than exploiting them: disassembly, decompilation support, tracing, symbolic execution, emulation, dynamic instrumentation, gadget analysis, and binary rewriting in the ctf environment.
Quick Start
Run inline Python in ctf:
python3 scripts/run_reversing_python.py --code 'import angr; print(angr.__version__)'
Run an analysis helper:
python3 scripts/run_reversing_python.py --file /absolute/path/to/analyze.py
Verify the mapped stack:
python3 scripts/verify_toolkit.py
Workflow
- Start with
toolbox_info,toolbox_verify, andtoolbox_capabilities. - Triage with
reversing_disassembleusing an explicitaddressorstart_addresswhen you already know the function entry. - Move to
reversing_decompileorreversing_read_databefore dropping into ad hoc scripts. - Use
reversing_emulate_blobfor deterministic execution of small code regions andreversing_symbolic_executewhen you need to solve for an input that reaches a target address. - Use
reversing_pythononly when the typed tools do not cover the analysis shape. - Read references/tooling.md when selecting among the installed reverse-engineering tools.
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 80 lines · 102 tokens per session scan A 332c30d7b7e1
opencrow-reversing-toolbox is a skill published in the GitHub repository 02loveslollipop/OpenCROW (8 stars, last pushed 3d ago), licensed Apache-2.0. It adds 102 tokens to every session and 1,028 once invoked, about $0.0005 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 2026-08-31.
Other skills, from other repositories
langsmith-tracing
LangSmith tracing and debugging setup for LLM applications. Configure observability, capture traces, and enable debugging for LangChain/LangGraph agents.
behavior-contract
Bug condition/postcondition formalization as testable Behavior Contracts. Defines invariants that must be preserved across fixes.
quality-hooks
Language-specific auto-lint/format/typecheck pipeline. Supports Python (ruff+pyright), TypeScript (prettier+eslint+tsc), Go (gofmt+golangci-lint). Auto-fix and convergence loops.
Reverse Engineering & Binary Analysis
Binary analysis, assembly interpretation, disassembly, decompilation, firmware RE, and protocol reverse engineering.
redteam-reverse-detail-pack
Domain routing and boundary guidance for authorized reverse engineering analysis, including decompilation, debugging, protocol reversing, firmware extraction, and deobfuscation. Use when a task belongs to the reverse engineering domain and needs scope, evidence, pivot, or exit criteria.
dd-risk-scoring
Calculate weighted risk scores from specialist agent reports. Use when synthesizing multiple due diligence reports into an overall investment risk assessment.