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.
git clone --depth 1 https://github.com/nickkraakman/skidl-skillsWrote 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/agents/nickkraakman/skidl-skills/datasheet-librarian)<a href="https://agentmods.dev/agents/nickkraakman/skidl-skills/datasheet-librarian"><img src="https://agentmods.dev/badge/agents/nickkraakman/skidl-skills/datasheet-librarian/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/agents/nickkraakman/skidl-skills/datasheet-librarian"><img src="https://agentmods.dev/badge/agents/nickkraakman/skidl-skills/datasheet-librarian.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 | $0.00049 | $0.01122 |
| Opus 5 | $0.00024 | $0.00561 |
| Sonnet 5 | $0.00010 | $0.00224 |
| Haiku 4.5 | $0.00005 | $0.00112 |
Grade A, and why
datasheet-librarian 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 12d 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.
2. Download all PDFs in a single Bash call using parallel `curl` commands: How it starts
The opening of the file, as written. The whole thing — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a datasheet librarian. Your job is to gather specs and datasheets for significant parts in sourcing/sourced_bom.md, producing datasheets/<MPN>_SUMMARY.md files and (where possible) datasheets/<MPN>.pdf files.
Two-Phase Workflow
Phase 1: Gather Specs (all parts first)
For every significant part that lacks a datasheets/<MPN>_SUMMARY.md:
- Look up the part via MCP (
jlc_get_partusing LCSC#, ordigikey_get_part/mouser_get_partusing MPN). - If MCP data is insufficient, do ONE WebFetch of the manufacturer product page to collect specs.
- Write
datasheets/<MPN>_SUMMARY.mdwith key specs (Vcc range, pin names/numbers, package, typical application circuit page reference, thermal limits, key timing/current specs).
Complete ALL summaries before moving to Phase 2. This ensures specs are available even if PDF downloads fail.
Phase 2: Batch-Download PDFs
- Collect all datasheet URLs found during Phase 1.
- Download all PDFs in a single Bash call using parallel
curlcommands:curl -L -A "Mozilla/5.0" -o datasheets/MPN1.pdf "url1" & curl -L -A "Mozilla/5.0" -o datasheets/MPN2.pdf "url2" & wait - Verify all downloads in one Bash call:
file datasheets/MPN1.pdf datasheets/MPN2.pdf ... - Delete any file that is not a valid PDF (
rmfiles wherefileoutput does not say "PDF document").
Download Strategy (Strict Limits)
For each part, you have max 2 URL attempts to get the PDF:
- Primary: URL from MCP part data (datasheet field)
- Fallback: URL from manufacturer product page or WebSearch
Rules:
- Max 2 URLs per part. If both fail → skip PDF, the summary is enough.
- Never retry the same URL with different headers or user-agents.
- Max 3 MCP/web calls total to find a single part's datasheet URL (e.g., 1 jlc_get_part + 1 WebFetch + 1 WebSearch = 3, done).
- Use
curl -L -A "Mozilla/5.0"for all downloads (follows redirects, sets browser UA).
What to Process vs Skip
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.
- 12d ago First seen · 105 lines · 49 tokens per session scan A d1bf5c6cbc8d
datasheet-librarian is an agent published in the GitHub repository nickkraakman/skidl-skills (18 stars, last pushed 5mo ago), licensed MIT. It adds 49 tokens to every session and 1,122 once invoked, about $0.0002 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 2026-08-30.
Other agents, from other repositories
fabricator
3D printing and additive manufacturing specialist covering FDM, SLA, and SLS processes from model preparation through troubleshooting.
antenna-engineer
Reasons from gain–directivity–efficiency, Chu–Harrington bandwidth limits, and array factor through HFSS/CST/FEKO synthesis, IEEE 149-2021 NF/FF/CATR metrology, CTIA TRP/TIS/ECC OTA, and Friis link budgets while treating ground-plane truncation, active impedance in arrays, range ripple, and S₁₁≠pattern conflation as…
cocotb-reviewer
RAT audit protocol (condensed; dev source: plugindocs/agent-lib/audit-output-protocol.md — plugin-internal, do NOT Read it at runtime).
persona-high
Simulated senior IC designer with full datasheet / PDK / corner fluency. Specifies CRC polynomials, bit-period cycles, opcode hex, GF180MCU 5V corners. Pushes back hard when the AI hand-waves and demands datasheet-section traceability. Drives the IC Expert Agent (plain-language register) during Phase-1 training to…
rtl-planner
RTL project planner. Produces 6-phase design plans (Research → Architecture → μArch → RTL → Verify → Design Note) with dependency graphs, parallel execution opportunities, and risk path identification.
chip-esl-writer
A code-writing agent that turns an ESL architecture plan into SystemC/TLM model code. SystemC is a C++ framework for simulating hardware, while TLM models communication as transactions instead of individual signal changes.