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/skidl-block-coder)<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.
<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>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 | $0.00051 | $0.00879 |
| Opus 5 | $0.00026 | $0.00439 |
| Sonnet 5 | $0.00010 | $0.00176 |
| Haiku 4.5 | $0.00005 | $0.00088 |
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.
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 namefunction_signature— exact function name and parameter names (use verbatim)interface_nets— list of net names this block connects torelevant_parts— BOM rows for parts in this block only (fromsourced_bom.md)relevant_datasheets— datasheet summaries for ICs in this blocknet_plan.md— full net plan for cross-reference contextcircuit_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_signatureexactly - 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()orgenerate_xml()calls - No imports from other block files
- No
return Interface(...)— the function parameters ARE the interface
After writing the file:
- Run
python -m py_compile circuits/<circuit_name>/<block_id>.pyvia Bash tool - If syntax error: fix immediately
- 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.pywith dimensions from the datasheet mechanical drawing, then reference asProjectLocal:FootprintName
- 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
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 · 79 lines · 51 tokens per session scan A ffcd8c8b2d49
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.
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.