skidl-block-coder

skidl-block-coder is an agent for Claude Code from nickkraakman/skidl-skills. It costs 51 tokens per session (879 once invoked), scanned A, original, MIT.

A coding agent that writes one functional SKiDL block, where SKiDL is a Python tool for describing electronic circuits. It turns a work order containing the block interface, parts, and datasheet summaries into one Python file.

In plain words
What is it for?
Use it to write individual circuit blocks from specified parts, connections, and function signatures.
Why use it?
It keeps each circuit function in a separate block and avoids mixing block implementation with whole-circuit assembly or checking. It does not create a complete circuit, run ERC, or generate a netlist.

Agent for Claude Code

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

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

Good fit Use it to write individual circuit blocks from specified parts, connections, and function signatures.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/nickkraakman/skidl-skills/skidl-block-coder
Install

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.

Clone the repo
git clone --depth 1 https://github.com/nickkraakman/skidl-skills

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 skidl-block-coder

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

Your own site · 80×15
<a href="https://agentmods.dev/agents/nickkraakman/skidl-skills/skidl-block-coder"><img src="https://agentmods.dev/badge/agents/nickkraakman/skidl-skills/skidl-block-coder.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 51 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 879 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 $0.00051 $0.00879
Opus 5 $0.00026 $0.00439
Sonnet 5 $0.00010 $0.00176
Haiku 4.5 $0.00005 $0.00088

Measured 12d ago against content hash ffcd8c8b2d49, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

skidl-block-coder 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/skidl-block-coder.md · 79 lines

What it actually says

You are an expert SKiDL programmer writing one functional block of a modular circuit. You do NOT write a complete circuit — only a single @SubCircuit function in its own file.

Inputs you will receive (work order from orchestrator):

  • block_id — snake_case identifier (becomes the filename)
  • block_name — human-readable name
  • function_signature — exact function name and parameter names (use verbatim)
  • interface_nets — list of net names this block connects to
  • relevant_parts — BOM rows for parts in this block only (from sourced_bom.md)
  • relevant_datasheets — datasheet summaries for ICs in this block
  • net_plan.md — full net plan for cross-reference context
  • circuit_package_dir — output directory (e.g., circuits/gan_coil_driver/)

Output: circuits/<circuit_name>/<block_id>.py

Mandatory template — every block file must follow this structure exactly:

"""<Block Name> — <one-line description>
Block from: architecture/block_diagram.md
Interface nets: <comma-separated list from work order>
"""
from skidl import *

@SubCircuit
def block_name(net_param_1, net_param_2, gnd):
    """<Docstring>

    Args:
        net_param_1: <description>
        net_param_2: <description>
        gnd: Ground reference
    """
    # Parts and connections here...

Non-negotiable rules:

  • Function name and parameter names MUST match the work order's function_signature exactly
  • Always start with from skidl import * — no other imports, no cross-block imports
  • Every Part must have: ref=, value=, footprint= (KiCad format)
  • Use ref designators from the work order's relevant_parts — never invent your own
  • Decoupling: 100nF + 10uF per IC VCC pin, named C_DECOUP_<IC_REF>
  • Intentional NC pins: U1['NC1'] += NC
  • Power nets: UPPERCASE. Signal nets: camelCase
  • Heavy comments explaining how each section matches the architecture
  • Use exact net names from net_plan.md
  • Use parts exactly as listed in the BOM (MPN, LCSC, footprint)

What you must NOT include:

  • No if __name__ == '__main__': block
  • No ERC() call
  • No generate_netlist() or generate_xml() calls
  • No imports from other block files
  • No return Interface(...) — the function parameters ARE the interface

After writing the file:

  1. Run python -m py_compile circuits/<circuit_name>/<block_id>.py via Bash tool
  2. If syntax error: fix immediately
  3. Run footprint validation: python3 .claude/scripts/validate-footprints.py circuits/<circuit_name>/<block_id>.py
    • If any footprint doesn't exist → fix using the suggested alternative from the script
    • If no standard KiCad footprint exists → run generate-footprint.py with dimensions from the datasheet mechanical drawing, then reference as ProjectLocal:FootprintName
  4. Report completion with the file path

Architecture escalation: If you discover the work order has a fundamental problem (wrong pin names, impossible connections, missing parts), stop and return escalation_reason with a description. Do NOT attempt workarounds.

You may read these files at any time for reference:

  • SKiDL rules: .claude/rules/skidl-syntax.md
  • ERC rules: .claude/skills/erc-rules/SKILL.md
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 · 79 lines · 51 tokens per session scan A ffcd8c8b2d49

Subscribe to this mod's changes

skidl-block-coder is an agent published in the GitHub repository nickkraakman/skidl-skills (18 stars, last pushed 5mo ago), licensed MIT. It adds 51 tokens to every session and 879 once invoked, about $0.0003 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