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 agentmods add commands/circuit-synth/kicad-sch-api/devgit clone --depth 1 https://github.com/circuit-synth/kicad-sch-apiWhat 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 | $0.00013 | $0.10083 |
| Opus 5 | $0.00006 | $0.05042 |
| Sonnet 5 | $0.00003 | $0.02017 |
| Haiku 4.5 | $0.00001 | $0.01008 |
Grade A, and why
dev scanned grade A with 1 finding 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 2d 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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
subprocess.run(["open", "/tmp/validation_demo.kicad_sch"]) How it starts
The opening of the file, as written. The whole thing — 1,314 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/dev - Development Workflow for KiCAD Schematic API
Purpose: Complete development workflow from problem description to pull request, using KiCAD reference-driven development with comprehensive testing and format preservation validation.
Use when: Building features, fixing bugs, or adding functionality that requires systematic development with PRD, reference schematics, tests, and iterative implementation.
Workflow Overview
/dev (end-to-end development)
├─ Phase 1: Generate PRD (research → ask questions → document)
│ └─ STOP: User reviews PRD
├─ Phase 2: Create Reference Schematic (Interactive - agent creates, user refines)
│ └─ STOP: User edits in KiCAD, says "done"
├─ Phase 3: Generate Tests (autonomous - no stop)
├─ Phase 4: Implementation (autonomous + communicative - shows progress)
│ └─ STOP if stuck after 8 iterations
├─ Phase 4.5: Manual Validation (Interactive - agent guides, user inspects)
│ └─ STOP: User validates in KiCAD
└─ Phase 5: Cleanup & PR (autonomous - no stop)
Time estimate: 1-4 hours depending on complexity
Reviewing and Fixing Existing PRs
If you encounter an existing PR with failing CI, follow these steps to fix it:
Step 1: Checkout the PR branch
gh pr checkout {PR_NUMBER}
Step 2: Fix formatting issues
# Format code
uv run black kicad_sch_api/ tests/
uv run isort kicad_sch_api/ tests/
Step 3: Fix other CI failures
# Run tests to identify failures
uv run pytest tests/ -v
# Fix type errors
uv run mypy kicad_sch_api/
# Fix linting issues
uv run flake8 kicad_sch_api/ tests/
Step 4: Commit and push fixes
git add -A
git commit -m "chore: Fix CI formatting and test failures
Apply black and isort formatting to pass CI checks.
Fix any test failures and type errors.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <[email protected]>"
git push origin {BRANCH_NAME}
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.
- 2d ago First seen · 1,314 lines · 13 tokens per session scan A 73023d9c1270
dev is a command published in the GitHub repository circuit-synth/kicad-sch-api (51 stars, last pushed 9mo ago), licensed MIT. It adds 13 tokens to every session and 10,083 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other commands, from other repositories
vibe-ic-benchmark
Run any known open IC-design benchmark (VerilogEval-v2/Human, RTLLM, CVDP, …) the CORRECT way per the open-benchmark-methodology skill. Auto-routes to the right run-shape (A/B/C/D), sets up the run dir scaffold, points at the blind instructions, and invokes the scorer. Use when "run benchmark X", "score benchmark X"…
vibe-ic-all
Run the complete Vibe-IC flow (Phase 1 → Phase 2 → Analog → Phase 3) via vibeiconeshotrunner. Auto-detects Path A vs B. AI-monitored + close-loop.
vibe-ic-phase2
Run Phase 2 (L1-L27 → RTL → SOF → byte[6]=0xF2) via designoneshotrunner. AI-monitored + bounded RTL repair/retry.
vibe-ic-phase3
Run Phase 3 (synth → PnR → GDS → DRC → LVS) via phase3oneshotrunner. AI-monitored + close-loop.
vibe-ic-phase23
Chain /vibe-ic-phase2 → /vibe-ic-phase3 via phase23oneshotrunner (true chained orchestrator — delegates to designoneshotrunner.py + phase3oneshotrunner.py, not monolithic). AI-monitored + close-loop.
review-branch
Purpose: Comprehensive branch analysis for code quality, security, performance, and risk assessment before merging to main. Specialized for circuit-synth development workflows.