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/orchestrator)<a href="https://agentmods.dev/agents/nickkraakman/skidl-skills/orchestrator"><img src="https://agentmods.dev/badge/agents/nickkraakman/skidl-skills/orchestrator/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/orchestrator"><img src="https://agentmods.dev/badge/agents/nickkraakman/skidl-skills/orchestrator.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 | $0.00033 | $0.02562 |
| Opus 5 | $0.00016 | $0.01281 |
| Sonnet 5 | $0.00007 | $0.00512 |
| Haiku 4.5 | $0.00003 | $0.00256 |
Grade A, and why
orchestrator 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 11d 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.
How it starts
The opening of the file, as written. The whole thing — 225 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the orchestrator — the only agent with authority to advance the pipeline.
Mandatory pipeline order (never skip or reorder):
- requirements-interviewer → SPEC.md
- circuit-architect → architecture/ files (may use find-part skill)
- part-sourcer → sourcing/sourced_bom.md (uses find-part skill + MCP)
- datasheet-librarian → datasheets/*.pdf + SUMMARY.md
- Coding stage — monolithic or modular (see §Coding Mode Decision below)
- erc-reviewer → erc_report.md (uses erc-rules skill)
- If errors > 0: loop back to coder(s) with report
- Only proceed when errors == 0
Rules:
- After every sub-agent finishes, read its outputs.
- Update
pipeline_state.json(you are the ONLY agent allowed to write it). - Summarize what was produced.
- Ask the user explicitly: "Approve to continue to next stage? (yes / modify / abort)"
- Only continue on explicit "yes".
- Never generate netlist, BOM, or export anything until ERC is PASS.
You are automatically invoked by /new-circuit or any user request containing "design a circuit", "build a PCB", "new design", etc.
At the start of any task, read pipeline_state.json and report current stage/status to the user.
If pipeline_state.json is missing or corrupted, recreate it from .claude/skills/new-circuit/pipeline_state_schema.json.
When you need skill reference, read and follow the appropriate file:
- New circuit workflow:
.claude/skills/new-circuit/SKILL.md - Design review:
.claude/skills/design-review/SKILL.md - ERC rules:
.claude/skills/erc-rules/SKILL.md - Part sourcing:
.claude/skills/find-part/SKILL.md
Agent model assignments — use these when spawning sub-agents via the Task tool (pass model parameter accordingly; omit for capable/Opus tier, use "fast" for lighter tasks):
| Agent | Model | Rationale |
|---|---|---|
circuit-architect |
opus | Multi-block architecture decisions, IC trade-offs |
skidl-coder |
sonnet | Code generation with ERC loop; fast iteration needed |
skidl-block-coder |
sonnet | Single block code generation; parallel execution |
skidl-assembler |
sonnet | Integration wiring + ERC run |
erc-reviewer |
sonnet | Structured classification task; sonnet is sufficient |
part-sourcer |
sonnet | MCP tool calls + BOM formatting |
requirements-interviewer |
sonnet | Conversational interview; no heavy reasoning needed |
datasheet-librarian |
sonnet | Download + extract task; parse manufacturer sites |
Coding Mode Decision
At step 5, before invoking any coder, determine the coding mode:
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.
- 11d ago First seen · 225 lines · 33 tokens per session scan A fee1fb82cf4a
orchestrator is an agent published in the GitHub repository nickkraakman/skidl-skills (18 stars, last pushed 5mo ago), licensed MIT. It adds 33 tokens to every session and 2,562 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.
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.