Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/Encod3d-Sec/TORCHnpx agentmods add skills/encod3d-sec/torch/pt-workflowWrote 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/encod3d-sec/torch/pt-workflow)<a href="https://agentmods.dev/skills/encod3d-sec/torch/pt-workflow"><img src="https://agentmods.dev/badge/skills/encod3d-sec/torch/pt-workflow/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/encod3d-sec/torch/pt-workflow"><img src="https://agentmods.dev/badge/skills/encod3d-sec/torch/pt-workflow.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 4 findings, up to critical
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- critical YARA Match · line 30 YARA rule matched a known malware signature (reverse shell, backdoor, ransomware, C2 framework, or info stealer).Fix: Remove the malware payload or compromised file entirely. Investigate how it entered the skill and audit all other artifacts for additional indicators of compromise.
- high YARA Match · line 24 YARA rule matched a hack tool or exploit indicator (offensive tools, reconnaissance, privilege escalation, or exploit frameworks).Fix: Remove offensive tool references and exploit code. Legitimate agent skills should not contain penetration testing tools, exploit frameworks, or reconnaissance utilities.
- high YARA Match · line 73 YARA rule matched a hack tool or exploit indicator (offensive tools, reconnaissance, privilege escalation, or exploit frameworks).Fix: Remove offensive tool references and exploit code. Legitimate agent skills should not contain penetration testing tools, exploit frameworks, or reconnaissance utilities.
- medium Excessive Agency · line 43 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00120 | $0.01576 |
| Opus 5.5 | $0.00048 | $0.00630 |
| Sonnet 5.5 | $0.00024 | $0.00315 |
| Haiku 4.5 | $0.00012 | $0.00158 |
Grade A, and why
pt-workflow 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 — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
pt-workflow
The driver is the plan. Run one command, do exactly what it prints, record the result, repeat. The
gates are enforced by scripts/campaign.py; follow its output literally.
The loop
python3 scripts/campaign.py next
python3 scripts/campaign.py note <row> --arsenal <slug>
python3 scripts/campaign.py done <row> --poc <img> --kind req # | --dead R | --park Q | --find F
Start / resume
python3 scripts/campaign.py init --type pt- validatesscope.md+ envelope, repairs type/schema. An emptyscope.mdmust be filled from the client SoW first (CIDRs, domains, RoE, lockout policy). The lockout policy and any destructive-op limits live inscope.md, not here.- Passes 1-3 feed
state.md- rustscan/nmap/nxc/LDAP/kerbrute/BloodHound per the recon defaults, which yield toscope.md's allowed tooling. Read service output end to end. python3 scripts/campaign.py board- writes the 4a rows (plus 4b lateral/privesc/DCSync for the pentest approach). Refuses on empty state.- Enter the loop, depth-first, one open row at a time.
- When a shell/session lands on a host (reverse shell via
vm-scan.sh --win shell, or meterpreter via--win msf), record it:python3 scripts/campaign.py foothold <host> --win shell(or ride it on the closing find withdone ... --win). The driver flips that host'sstate.mdrow toaccess=foothold, routes its 4b lateral/privesc rows throughvm-rsh --win <win>(persistent session + operator visibility), and printstmux attach -t <eng>for takeover.
Gates
Same as the shared driver: G1 arsenal-first, G2 skill-first, G3 typed evidence, G8 tool-first. AD
attacks route through Skill(hunt-ad); local privesc through Skill(hunt-windows) /
Skill(hunt-macos); the driver names which per row.
Autonomy
No approvals. Out-of-envelope work parks to decisions.md; the loop never blocks. A spray is gated by
the lockout policy in scope.md (the envelope), never attempted blind. Destructive AD operations
(Zerologon and similar) park unless the envelope authorises them.
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 · 89 lines · 120 tokens per session scan A 67d454fa4b61
pt-workflow is a skill published in the GitHub repository Encod3d-Sec/TORCH (336 stars, last pushed 1mo ago), licensed MIT. It adds 120 tokens to every session and 1,576 once invoked, about $0.0005 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.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…