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/bb-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/bb-workflow)<a href="https://agentmods.dev/skills/encod3d-sec/torch/bb-workflow"><img src="https://agentmods.dev/badge/skills/encod3d-sec/torch/bb-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/bb-workflow"><img src="https://agentmods.dev/badge/skills/encod3d-sec/torch/bb-workflow.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to high
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 →
- high YARA Match · line 92 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 63 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 | $0.01871 |
| Opus 5.5 | $0.00048 | $0.00748 |
| Sonnet 5.5 | $0.00024 | $0.00374 |
| Haiku 4.5 | $0.00012 | $0.00187 |
Grade A, and why
bb-workflow scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
`curl` - a modern site's real attack surface is only visible rendered. Use the `chrome-devtools` MCP: How it starts
The opening of the file, as written. The whole thing — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
bb-workflow
The driver is the plan. You run one command, do exactly what it prints, record the result, repeat.
Nothing here is advisory: the gates are enforced by scripts/campaign.py, so follow its output
literally rather than improvising. This exists because prose routing failed - 22 Skill calls against
341 hand-rolled curls in the reference campaign; the board fixes that by making the mandate tool
output, fresh every turn.
The loop
python3 scripts/campaign.py next # prints ONE required-action block
# do EXACTLY what it lists, in order
python3 scripts/campaign.py note <row> --arsenal <slug> # after Skill(wiki-arsenal)
python3 scripts/campaign.py done <row> --poc <img> --kind req # | --dead R | --park Q | --find F
# repeat
Start / resume
python3 scripts/campaign.py init --type bb- validatesscope.md+ the autonomy envelope, repairsengagement_type/schema, prints the Deadends size. If it exits 2, fix what it names (an emptyscope.mdis the one thing it cannot invent - fill it from the programme brief first).- Passes 0-3 (OSINT/Wayback, crawl, fingerprint, CVE) feed
state.md. Read every JS bundle and handler end to end (Skill-less; volume-reduce first: source-map, drop vendor, beautify, read). Grep never substitutes for the read. python3 scripts/campaign.py board- writes the killchain 4a rows. Refuses on an empty state.- Enter the loop.
nextserves one row, depth-first, one open row at a time.
Browser observation (chrome-devtools MCP)
The programme's targets are internet-reachable, so drive them through a real browser, not just
curl - a modern site's real attack surface is only visible rendered. Use the chrome-devtools MCP:
- Pass 1 crawl:
navigate_pageto each app, thenlist_network_requests- the XHR/fetch calls a page makes reveal the API endpoints/routes a static crawl never sees (this is exactly the lead a curl-only recon misses).take_snapshotfor the rendered DOM;evaluate_scriptto read client config /__NEXT_DATA__/ JS globals. - Confirmation + evidence: DOM-XSS fires in the real DOM (
evaluate_script/ console); a renderedtake_screenshotof the exploited state is a validwebPoC (G3).
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 · 108 lines · 120 tokens per session scan A c027c95d0ec6
bb-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 1,871 once invoked, about $0.0005 per session on Opus 5.5. A static security scan graded it A with 1 finding (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
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…