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 agentmods add skills/agentcomputerai/torch/digikeynpx skills add AgentComputerAI/torch --skill digikeygit clone --depth 1 https://github.com/AgentComputerAI/torchWhat 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 | $0.00140 | $0.02305 |
| Opus 5 | $0.00070 | $0.01153 |
| Sonnet 5 | $0.00028 | $0.00461 |
| Haiku 4.5 | $0.00014 | $0.00231 |
Grade A, and why
digikey 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 2d 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.
description: Proven scraping playbook for digikey.com /en/products/category/ listings. Cloudflare challenge (cf-mitigated: challenge) blocks bare curl with HTTP 403, but a puppeteer connection to the user's real Chrome v How it starts
The opening of the file, as written. The whole thing — 155 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DigiKey (digikey.com)
Cloudflare-protected catalog with a fully server-rendered HTML product table. Real Chrome connect kills the challenge in one navigation. Pure DOM scrape — no API replay needed, every parametric column is in the table.
Detection
| Signal | Value |
|---|---|
| CDN | Cloudflare (server: cloudflare, cf-ray) |
| Anti-bot | Cloudflare challenge — cf-mitigated: challenge, HTTP 403 on bare curl |
| Framework | Server-rendered HTML (no __NEXT_DATA__, no SPA hydration needed) |
| Auth | Not required |
| Captcha | None visible after CF clears |
Bare curl https://www.digikey.com/en/products/category/microcontrollers/685 returns:
HTTP/2 403
cf-mitigated: challenge
server: cloudflare
…with a 4.7KB challenge HTML body. Fetch / node-fetch / requests are all blocked the same way.
Architecture
- Single canonical category URL:
/en/products/category/<slug>/<id>(e.g. microcontrollers = 685). - HTML returned by Cloudflare-cleared session contains a
<table>with:<thead><th>cells for ~28 columns: blank (image),Mfr Part #,Quantity Available,Price,Tariff Status,Series,Package,Product Status,DigiKey Programmable,Core Processor,Core Size,Speed,Connectivity,Peripherals,Number of I/O,Program Memory Size,Program Memory Type,EEPROM Size,RAM Size,Voltage - Supply (Vcc/Vdd),Data Converters,Oscillator Type,Operating Temperature,Grade,Qualification,Mounting Type,Supplier Device Package,Package / Case.<tbody><tr>rows, 25 per page by default. Each row hasa[href*="/en/products/detail/<mfg>/<part>/<digikey-id>"]and a thumbnail<img>frommm.digikey.com.
- Column set varies by category (microcontrollers exposes core/speed/memory; capacitors expose capacitance/voltage/ESR/etc.). Don't hard-code columns — read
<thead>and zip. - The only XHR seen during page load is
/en/api/scTools/Header2021/GeoInfo(geo banner). No internal product API call is needed — everything is in the SSR HTML.
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.
- 2d ago First seen · 155 lines · 0 tokens per session scan A 037f55eeae52
digikey is a skill published in the GitHub repository AgentComputerAI/torch (5 stars, last pushed 4mo ago), licensed MIT. It adds 140 tokens to every session and 2,305 once invoked, about $0.0007 per session on Opus 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 2026-08-31.
Other skills, from other repositories
br3eze-code
AgentOS uses a modular 3-tier ReAct reasoning engine. The AI (Gemini 2.0 Flash / Claude Sonnet 4.6 / GPT-4o / Ollama) automatically discovers, chains, and executes these skills via the Tool Registry and Skill Loader.
agentos-security-remediation
Review and remediate Dependabot and dependency vulnerabilities in AgentOS repositories. Use for critical or high-severity alert triage, dependency-path analysis, specialist assignment, secure upgrades, regression testing, rollback planning, release gates, and audit evidence.
agentos-specialist-swarm
Coordinate AgentOS specialist work across Planner, Engineer, Accountant, Secretary, Procurement, Expeditor, Designer, and Draftsman roles. Use for role onboarding, WBS delegation, skill selection, activity tracking, handoffs, approvals, evidence, channel rendering, procurement exceptions, and project delivery…
agentos-expeditor
Coordinate AgentOS fulfillment and delivery work with milestones, supplier and courier tracking, exception handling, recovery options, Procurement handoffs, escalation approvals, evidence, and receipt closure. Use for order delays, shipment tracking, vendor exceptions, and delivery recovery.
agentos-role-skill-factory
Create, validate, integrate, and release separate AgentOS role-skill packages with SKILL.md instructions and index.js entry points. Use when adding a specialist role, generating role metadata, wiring WBS and approval contracts, or packaging role skills for the repository.
agentos-designer
Design user, service, and system solutions in AgentOS from scoped requirements, constraints, alternatives, prototypes, reviews, acceptance criteria, and controlled publication. Use for design briefs, concepts, UX, service flows, architecture proposals, and design changes.