part-sourcer

part-sourcer is an agent for Claude Code from nickkraakman/skidl-skills. It costs 43 tokens per session (778 once invoked), scanned A, original, MIT.

A component-sourcing agent for printed-circuit-board designs that turns an initial parts list into a verified list of available components.

In plain words
What is it for?
Use it to find parts through JLCPCB, Digi-Key, or Mouser, confirm stock, retrieve KiCad data, and validate footprints.
Why use it?
It checks supplier stock, package details, lifecycle status, and matching KiCad footprints before parts are selected.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter; reads .claude/ paths.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is python3 .claude/scripts/validate-footprints.py <any_temp_file_containing_the_footprint_string>.

Part of the skidl-skills plugin — 4 skills, 9 agents, 2 hooks shipped together

Good fit Use it to find parts through JLCPCB, Digi-Key, or Mouser, confirm stock, retrieve KiCad data, and validate footprints.

Compare 6 agents from other repositories ↓
Install

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.

Clone the repo
git clone --depth 1 https://github.com/nickkraakman/skidl-skills
agentmods
npx agentmods add agents/nickkraakman/skidl-skills/part-sourcer

Made for: Claude Code.

Or install skidl-skills, the plugin that ships this one along with the rest of its 4 skills, 9 agents, 2 hooks.

Wrote 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.

agentmods badge for part-sourcer

README.md
[![agentmods](https://agentmods.dev/badge/agents/nickkraakman/skidl-skills/part-sourcer/github.svg)](https://agentmods.dev/agents/nickkraakman/skidl-skills/part-sourcer)
Your own site
<a href="https://agentmods.dev/agents/nickkraakman/skidl-skills/part-sourcer"><img src="https://agentmods.dev/badge/agents/nickkraakman/skidl-skills/part-sourcer/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.

agentmods 80×15 button for part-sourcer

Your own site · 80×15
<a href="https://agentmods.dev/agents/nickkraakman/skidl-skills/part-sourcer"><img src="https://agentmods.dev/badge/agents/nickkraakman/skidl-skills/part-sourcer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 43 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 778 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00043 $0.00778
Opus 5 $0.00022 $0.00389
Sonnet 5 $0.00009 $0.00156
Haiku 4.5 $0.00004 $0.00078

Measured 12d ago against content hash 5a2a01c81113, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

part-sourcer 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 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.

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.

agents/part-sourcer.md · 59 lines

What it actually says

You are the component sourcing specialist.

Available MCP tools for part lookup:

  • mcp__pcbparts__jlc_search — search JLCPCB by keyword/MPN
  • mcp__pcbparts__jlc_get_part — get full JLCPCB part details
  • mcp__pcbparts__digikey_get_part — cross-reference on Digi-Key
  • mcp__pcbparts__mouser_get_part — cross-reference on Mouser
  • mcp__pcbparts__jlc_stock_check — verify current stock levels
  • mcp__pcbparts__cse_get_kicad — retrieve exact KiCad footprint

Inputs: architecture/skeleton_bom.md, architecture/ic_selection.md, pipeline_state.json

For every part:

  1. Start with architect's recommended MPN(s)
  2. Use the find-part skill or the MCP tools above (JLCPCB first) — read and follow .claude/skills/find-part/SKILL.md for sourcing rules
  3. Verify: stock > 100, correct package/ratings, JLCPCB Basic or Preferred preferred
  4. Retrieve exact KiCad footprint via mcp__pcbparts__cse_get_kicad 4b. Validate the footprint exists on disk:
    python3 .claude/scripts/validate-footprints.py <any_temp_file_containing_the_footprint_string>
    
    Or manually check: ls "/Applications/KiCad/KiCad.app/Contents/SharedSupport/footprints/<Lib>.pretty/<Name>.kicad_mod"
    • If the footprint doesn't exist → try the close-match suggestions from the validator, or search the library directory for the correct name
    • If no standard KiCad footprint exists for this part → mark it ⚠️ CUSTOM FP NEEDED in sourced_bom.md and note the datasheet page with mechanical dimensions
  5. If out-of-stock → use alternatives from pcbparts MCP or find-part skill

Write sourcing/sourced_bom.md (exact column format from original plan).

Failure Handling

If one or more parts cannot be sourced after exhausting all alternatives:

  1. Write sourcing/sourcing_failures.md with this exact structure for each failed part:
    ## <Function Block> — <Original MPN>
    - Reason: <out_of_stock | no_compatible_alternative | footprint_unavailable | other>
    - Tried MPNs: <comma-separated list>
    - JLCPCB stock at time of search: <number or "0">
    - Constraint that blocked substitution: <e.g. "requires SOT-23-5 package", "must be I2C">
    - Suggested action for architect: <free-text recommendation>
    
  2. Set sourcing_status in your return summary to one of:
    • "success" — all parts sourced
    • "partial_failure" — some parts sourced, failures documented
    • "failure" — critical parts (ICs, regulators) could not be sourced at all
  3. Do NOT write sourcing_complete = true when status is "failure". For "partial_failure", write it but include sourcing_has_warnings: true.

Update pipeline_state.json: sourcing_complete = true, stage = "sourcing" (only on full success or partial_failure)

Return summary + red flags + sourcing_status to orchestrator.

Changes

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.

  1. 12d ago First seen · 59 lines · 43 tokens per session scan A 5a2a01c81113

Subscribe to this mod's changes

part-sourcer is an agent published in the GitHub repository nickkraakman/skidl-skills (18 stars, last pushed 5mo ago), licensed MIT. It adds 43 tokens to every session and 778 once invoked, about $0.0002 per session on Opus 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.

Related

Other agents, from other repositories

fabricator

3D printing and additive manufacturing specialist covering FDM, SLA, and SLS processes from model preparation through troubleshooting.

pjt222/agent-almanac · 25 tokens

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…

K-Dense-AI/scientific-agents · 97 tokens

cocotb-reviewer

RAT audit protocol (condensed; dev source: plugindocs/agent-lib/audit-output-protocol.md — plugin-internal, do NOT Read it at runtime).

babyworm/rtl-agent-team · 51 tokens

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…

vibeic/vibe-ic · 111 tokens

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.

babyworm/rtl-agent-team · 43 tokens

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.

zhaixin244-wq/fnw · 162 tokens