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 reverse-shell-asyncgit 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/reverse-shell-async)<a href="https://agentmods.dev/skills/02loveslollipop/opencrow/reverse-shell-async"><img src="https://agentmods.dev/badge/skills/02loveslollipop/opencrow/reverse-shell-async/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/reverse-shell-async"><img src="https://agentmods.dev/badge/skills/02loveslollipop/opencrow/reverse-shell-async.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 | $0.00061 | $0.00813 |
| Opus 5.5 | $0.00024 | $0.00325 |
| Sonnet 5.5 | $0.00012 | $0.00163 |
| Haiku 4.5 | $0.00006 | $0.00081 |
Grade A, and why
reverse-shell-async 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 1mo 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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OpenCROW I/O - Reverse Shell Async
Use this skill only for authorized CTF challenges, isolated labs, or systems you own. It manages the listener side of one inbound TCP session. It does not generate, suggest, or deploy reverse-shell payloads.
Runtime preflight
Prefer the opencrow-netcat-mcp server in a full installation. Start with toolbox_info, toolbox_verify, and toolbox_capabilities, then use session_listen. In a skills-only installation, probe rsx with command -v rsx; if it is unavailable, use the relative scripts/rsx resource. Report the exact missing command if neither path exists.
Safety defaults
- The listener binds to
127.0.0.1unless--bind-hostis supplied. - A non-loopback bind is rejected unless
--allow-remoteis explicit. - Use
--expected-peer IP_OR_CIDRwhenever the peer address is known. Mismatches are logged, closed, and do not consume the listener. - A named listener accepts exactly one matching connection. It does not reconnect and does not serve multiple clients.
- Use a distinct session name for each authorized target flow, and stop live sessions when work is complete.
MCP-first workflow
- Call
session_listenwith a name and port. Port0requests an available local port; read the actual port from the returned status. - Poll
session_statusuntil its state isconnected. - Use
session_sendwith exactly one ofdata,hex, orbase64. - Use
session_readfor the escaped event log. Treat therx.rawartifact as the exact received bytes. - Call
session_stopif the listener or connection is still running.
CLI fallback
# Loopback listener on an automatically selected port
rsx listen --name lab --port 0
# Explicit authorized remote listener restricted to one source CIDR
rsx listen --name lab --bind-host 0.0.0.0 --port 4444 \
--allow-remote --expected-peer 192.0.2.25/32
# Text and exact-byte input
rsx send --name lab --data 'id' --newline
rsx send --name lab --hex '03'
rsx send --name lab --base64 'AAEC/w=='
# Observe and stop
rsx status --name lab
rsx read --name lab --tail 40
rsx stop --name lab
What ships with it
2 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.
- 1mo ago First seen · 66 lines · 61 tokens per session scan A 514084699cf4
reverse-shell-async is a skill published in the GitHub repository 02loveslollipop/OpenCROW (10 stars, last pushed yesterday), licensed Apache-2.0. It adds 61 tokens to every session and 813 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
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-synthesis
Synthesize findings from multiple specialist agents into a coherent investment recommendation. Use when combining reports from 9+ specialist agents into a single decision document.
dd-report-format
Standard output format for due diligence analysis reports. Use when producing your final analysis to ensure consistency across all specialist agents.
dd-risk-scoring
Calculate weighted risk scores from specialist agent reports. Use when synthesizing multiple due diligence reports into an overall investment risk assessment.
dd-sourcing
Document sources properly for due diligence reports. Use when citing any external data, ensuring full traceability and auditability of findings.
dd-verification
Verify claims in pitch decks and founder statements using multiple independent sources. Use when analyzing any claim about market size, traction, team background, or competitive positioning.