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.
npx skills add salitronic/eda-agent --skill autodesigngit clone --depth 1 https://github.com/salitronic/eda-agentWrote 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/skills/salitronic/eda-agent/autodesign)<a href="https://agentmods.dev/skills/salitronic/eda-agent/autodesign"><img src="https://agentmods.dev/badge/skills/salitronic/eda-agent/autodesign/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/skills/salitronic/eda-agent/autodesign"><img src="https://agentmods.dev/badge/skills/salitronic/eda-agent/autodesign.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00100 | $0.01107 |
| Opus 5.5 | $0.00040 | $0.00443 |
| Sonnet 5.5 | $0.00020 | $0.00221 |
| Haiku 4.5 | $0.00010 | $0.00111 |
Grade A, and why
autodesign 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 23d 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 — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Autonomous PCB design (eda-agent)
Drive a full spec-to-board design by looping the server-side state machine.
The server owns sequencing, gates, and durable state, so you never memorize
the workflow: you call design_next_action, do what it says, log the
result, and repeat. A weaker model produces a plainer board, never a broken
pipeline, because the integrity lives server-side.
Before you start
- Confirm the editor is actually answering, with
app_pingon Altium oreasyeda_pingon EasyEDA. Ping, notapp_get_status: status reports that the process exists and that something once called attach, and neither of those proves the bridge replies. If it does not answer, tell the user how to start it; don't guess. - Read
design_get_disciplineonce: the hard rules and the DesignPlan schema. Or calldesign_autonomy_guidefor the full protocol + the 13 stages with their tools and exit gates.
The loop
design_session_start(requirement)opens the durable journal. Keep the returnedsession_id; every later call takes it. Thendesign_live_viewso the user can watch the board change, and record each decision with its reason before acting on it (design_live_note).- If a project is open or will be modified, checkpoint first so the whole
run is revertible in one step:
app_checkpoint("before autonomous run")on Altium,easyeda_checkpointon EasyEDA. - Loop:
design_next_action(session_id)and act onstatus:- proceed / retry: do the stage using its
suggested_toolsuntil theexit_gateis met, thendesign_session_log(event="stage_result", stage=<stage>, status="ok"). Where the gate names numbers (placement, routing, pours, verification), measure them withpcb_layout_auditand pass the result asdata=: the harness checks them and sends the stage back if one fails. If you cannot finish without the user, logstatus="blocked"with a question and stop. - blocked: put
open_questionto the user; when answered,design_session_log(event="resolved", text=<answer>)and continue. - complete: the 13 stages are done; write the design report with
design_session_reportand review outputs with the user.
- proceed / retry: do the stage using its
- Checkpoint again before each high-risk mutating stage:
sch_to_pcb,routing,pours_tuning. - Long engine runs (routing a dense board) can exceed the tool timeout;
start them with
design_job_startand polldesign_job_status/design_job_result.
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.
- 23d ago Changed · +16 lines b7ba9daf9de2
- 1mo ago First seen · 74 lines · 100 tokens per session scan A 5d31607b9b4b
autodesign is a skill published in the GitHub repository salitronic/eda-agent (290 stars, last pushed today), licensed Apache-2.0. It adds 100 tokens to every session and 1,107 once invoked, about $0.0004 per session on Opus 5.5. 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 skills, from other repositories
altium-library
Create and verify Altium schematic symbols (.SchLib) and PCB footprints (.PcbLib) from datasheets and 2D drawings, as code. Use whenever a part library must be made, fixed, measured from a drawing, or checked. Triggers: "make a footprint", "create a symbol", "add this part to the library", "SchLib", "PcbLib"…
altium-designer
Automate Altium Designer PCB workflows with DXP scripts, design-rule checks, OutJob fabrication outputs, and routing configuration.
universal-netlist
Query EDA netlists from the shell with the universal-netlist command line: Cadence OrCAD .DSN, Altium .PrjPcb, KiCad .kicadpro and Universal Netlist .netlist.json. Finds designs, searches nets and components, traces connectivity across passives (XNETs), and runs electrical rule checks. Use when reviewing a schematic…
altium-pcb-placement
Altium PCB component placement — derive board size, decide rotation for main ICs and connectors, split zones, generate a 1:1 placement plan drawing, then inject real coordinates after approval, and check overlaps. Triggers: "PCB placement", "place the components", "how big should the board be", "board outline", "start…
altium-schematic-review
Review an Altium schematic (.SchDoc) — find unconnected pins, missing footprint links and net errors, then judge each candidate against the datasheet before calling it a defect. Triggers: "review this schematic", "check my circuit", "ERC", "floating pins", "unconnected", "any missing footprints", "does this schematic…
kicad
Analyze KiCad projects and PDF schematics: schematics, PCB layouts, Gerbers, footprints, symbols, netlists, and design rules. Reviews designs for bugs, traces nets, cross-references schematic to PCB, extracts BOM data, checks DRC/ERC, DFM, power trees, and regulator circuits. Every finding carries a confidence label…