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 blacklanternsecurity/red-run --skill pivoting-tunnelinggit clone --depth 1 https://github.com/blacklanternsecurity/red-runWrote 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/blacklanternsecurity/red-run/pivoting-tunneling)<a href="https://agentmods.dev/skills/blacklanternsecurity/red-run/pivoting-tunneling"><img src="https://agentmods.dev/badge/skills/blacklanternsecurity/red-run/pivoting-tunneling/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/blacklanternsecurity/red-run/pivoting-tunneling"><img src="https://agentmods.dev/badge/skills/blacklanternsecurity/red-run/pivoting-tunneling.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 | $0.00024 | $0.09389 |
| Opus 5 | $0.00012 | $0.04695 |
| Sonnet 5 | $0.00005 | $0.01878 |
| Haiku 4.5 | $0.00002 | $0.00939 |
Grade B, and why
pivoting-tunneling scanned grade B with 2 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 9d 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
- Requires root/sudo on the attacker machine (uses iptables/pf) Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
proxychains curl http://10.10.10.5/ The source is not reproduced here
Licensed GPL-3.0
The repository is licensed GPL-3.0, which this catalogue does not treat as permission to reproduce the file. Read it at the source.
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.
- 9d ago First seen · 1,137 lines · 24 tokens per session scan B 97aa92432d34
pivoting-tunneling is a skill published in the GitHub repository blacklanternsecurity/red-run (267 stars, last pushed 5mo ago), licensed GPL-3.0. It adds 24 tokens to every session and 9,389 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 2 findings (asks for root, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
portr-cli
Use when an AI agent or harness needs to operate the Portr CLI: authenticate a client, add users to teams, create HTTP/WebSocket/TCP/stub tunnels, run config-defined tunnels, inspect request logs, replay captured requests, or control tunnels through the local app-server API. This skill is compatible with Claude Code…
huawei-cloud-devbridge-tunnel
Create and manage DevBridge development tunnels on Huawei Cloud to securely expose local development services to remote devices. Based on DevBridge CLI v0.1.12+ and Huawei Cloud IAM authentication. Use this skill when the user wants to: (1) install and configure the DevBridge CLI, (2) create/list/update/delete…
apply-lean-startup-methodology
Use when a validated problem is ready to move into building — deciding what minimum viable product to build first, what to measure to test whether it actually solves the problem, and whether to pivot or persevere — bridging the gap between problem-validation interviews and post-launch growth experimentation.
ssh
A guide to using SSH, a secure way to connect to and run commands on another computer. It covers connections, configuration files, login keys, jump hosts, port forwarding, and basic security settings.
data-analysis
A set of spreadsheet practices for interpreting data and presenting conclusions. It covers statistical measures, trend analysis, pivot-style summaries, charts, and written findings.
service_expose
Run user-created frontend/backend/WebSocket services and expose them through Cloudflare by default when the user asks to start, deploy, preview, share, or make the service accessible. Local-only is allowed only when explicitly requested.