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 sheares/easyeda-mcp-fix --skill pcb-lintgit clone --depth 1 https://github.com/sheares/easyeda-mcp-fixWrote 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/sheares/easyeda-mcp-fix/pcb-lint)<a href="https://agentmods.dev/skills/sheares/easyeda-mcp-fix/pcb-lint"><img src="https://agentmods.dev/badge/skills/sheares/easyeda-mcp-fix/pcb-lint/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/sheares/easyeda-mcp-fix/pcb-lint"><img src="https://agentmods.dev/badge/skills/sheares/easyeda-mcp-fix/pcb-lint.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 | $0.00108 | $0.06303 |
| Opus 5.5 | $0.00043 | $0.02521 |
| Sonnet 5.5 | $0.00022 | $0.01261 |
| Haiku 4.5 | $0.00011 | $0.00630 |
Grade A, and why
pcb-lint 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 10d 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 — 290 lines — stays where its author put it; the contents beside it link to each section on GitHub.
pcb-lint
A structured design-hygiene pass over the board open in EasyEDA Pro. You (Claude) call the mcp__easyeda__* tools directly, apply the check rules below, and write a markdown report plus a JSON sidecar.
It is a second pair of eyes, not a sign-off. It catches the common, expensive mistakes (an overvoltage regulator divider, a USB-C port that never gets power, copper too close to the board edge) before you pay for boards. It does not replace reading the datasheets or the fab's own DRC.
What is in this folder
SKILL.md(this file): the operational rules you follow.scripts/checks/{sch,pcb}_*.py: a Python reference implementation of 25 of the 26 checks, unit-tested against mock MCP payloads (tests/, 189 tests). When a rule below is ambiguous, read the Python. If the Python and this file disagree, the Python is the truth.scripts/config.example.json: a template for the optional per-board config.
The Python is a test harness and reference, not the runner. You are the runner.
Invocation modes
/pcb-lint(no arguments): run all checks and assemble one report grouped by severity. The normal path./pcb-lint sch: schematic checks only (SCH-*). Use when the schematic exists but the PCB is not laid out yet./pcb-lint pcb: PCB checks only (PCB-*)./pcb-lint <check-id>(for example/pcb-lint PCB-21): one check only. Use to iterate quickly while fixing one class of finding.
Preconditions
- EasyEDA Pro is running with the target project open.
- The bridge is live. Call
mcp__easyeda__server_infofirst. If the call fails, orextensionConnectedis false, orconnectedInstanceCountis 0, tell the user the extension is not connected (in EasyEDA Pro: Claude → Connect Claude in the top menu) and stop. Do not run checks against a dead bridge. - The right board is active. Call
mcp__easyeda__editor_get_open_tabsand confirm the active tab is the board the user means. If several EasyEDA windows are open, usemcp__easyeda__list_instancesand pass the rightinstance_id. - Config file (optional). Look for
pcb-lint.config.jsonin the project folder the user is working from. If absent, run with defaults and emit aCONFIG-01info finding pointing atscripts/config.example.json.
What ships with it
60 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- pyproject.toml 510 B
- README.md 2.5 KB
- scripts/checks/__init__.py 1.6 KB runs code
- scripts/checks/base.py 2.0 KB runs code
- scripts/checks/pcb_01_drc.py 1.1 KB runs code
- scripts/checks/pcb_02_decoupling_proximity.py 5.7 KB runs code
- scripts/checks/pcb_03_three_w_spacing.py 5.1 KB runs code
- scripts/checks/pcb_05_tvs_proximity.py 4.7 KB runs code
- scripts/checks/pcb_08_annular_ring.py 2.4 KB runs code
- scripts/checks/pcb_10_testpoints.py 1.8 KB runs code
- scripts/checks/pcb_11_fiducials.py 1.7 KB runs code
- scripts/checks/pcb_13_mil_coord_sanity.py 1.5 KB runs code
- scripts/checks/pcb_14_soldermask_expansion.py 4.3 KB runs code
- scripts/checks/pcb_18_via_aspect_ratio.py 1.9 KB runs code
- scripts/checks/pcb_19_diff_pair_via_balance.py 2.7 KB runs code
- scripts/checks/pcb_20_mask_dam_width.py 9.9 KB runs code
- scripts/checks/pcb_21_edge_clearance.py 16 KB runs code
- scripts/checks/pcb_22_antenna_keepout.py 22 KB runs code
- scripts/checks/sch_01_erc.py 1.7 KB runs code
- scripts/checks/sch_02_decoupling.py 3.7 KB runs code
- scripts/checks/sch_03_power_symbols.py 2.0 KB runs code
- scripts/checks/sch_04_net_naming.py 1.4 KB runs code
- scripts/checks/sch_05_bom_complete.py 2.3 KB runs code
- scripts/checks/sch_06_jlc_stock.py 1.6 KB runs code
- scripts/checks/sch_07_bulk_cap.py 4.1 KB runs code
- scripts/checks/sch_08_regulator_vout.py 18 KB runs code
- scripts/checks/sch_09_driver_com_pin.py 7.6 KB runs code
- scripts/checks/sch_10_usbc_cc_resistors.py 8.1 KB runs code
- scripts/checks/sch_11_esp32_strapping.py 38 KB runs code
- scripts/checks/types.py 16 KB runs code
- scripts/config.example.json 774 B
- scripts/mcp_client.py 5.4 KB runs code
- scripts/reporters/__init__.py 0 B runs code
- scripts/reporters/json_report.py 327 B runs code
- scripts/reporters/markdown.py 2.7 KB runs code
- scripts/runner.py 4.8 KB runs code
- tests/conftest.py 3.8 KB runs code
- tests/fixtures/.gitkeep 0 B
- tests/test_pcb_01_drc.py 589 B runs code
- tests/test_pcb_02_decoupling_proximity.py 1.8 KB runs code
- tests/test_pcb_03_three_w_spacing.py 4.0 KB runs code
- tests/test_pcb_05_tvs_proximity.py 1.5 KB runs code
- tests/test_pcb_08_annular_ring.py 2.3 KB runs code
- tests/test_pcb_10_testpoints.py 903 B runs code
- tests/test_pcb_11_fiducials.py 741 B runs code
- tests/test_pcb_13_mil_coord_sanity.py 856 B runs code
- tests/test_pcb_14_soldermask_expansion.py 2.4 KB runs code
- tests/test_pcb_18_via_aspect_ratio.py 1.3 KB runs code
- tests/test_pcb_19_diff_pair_via_balance.py 1.5 KB runs code
- tests/test_pcb_20_mask_dam.py 16 KB runs code
- tests/test_pcb_21_edge_clearance.py 13 KB runs code
- tests/test_pcb_22_antenna_keepout.py 16 KB runs code
- tests/test_sch_01_erc.py 1.3 KB runs code
- tests/test_sch_02_decoupling.py 2.1 KB runs code
- tests/test_sch_03_power_symbols.py 1.3 KB runs code
- tests/test_sch_04_net_naming.py 832 B runs code
- tests/test_sch_05_bom_complete.py 1.6 KB runs code
- tests/test_sch_06_jlc_stock.py 693 B runs code
- tests/test_sch_07_bulk_cap.py 3.3 KB runs code
- tests/test_sch_08_regulator_vout.py 15 KB runs code
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.
- 10d ago First seen · 290 lines · 108 tokens per session scan A d5077c4163d4
pcb-lint is a skill published in the GitHub repository sheares/easyeda-mcp-fix (0 stars, last pushed today), licensed MIT. It adds 108 tokens to every session and 6,303 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 2026-10-05.
Other skills, from other repositories
tdd-workflow
Use this skill when writing new features, fixing bugs, or refactoring code. Enforces test-driven development with 80%+ coverage including unit, integration, and E2E tests.
rust-testing
Rust testing patterns including unit tests, integration tests, async testing, property-based testing, mocking, and coverage. Follows TDD methodology.
cpp-testing
Use only when writing/updating/fixing C++ tests, configuring GoogleTest/CTest, diagnosing failing or flaky tests, or adding coverage/sanitizers.
golang-testing
Go testing best practices including table-driven tests, test helpers, benchmarking, race detection, coverage analysis, and integration testing patterns. Use when writing or improving Go tests.
swift-protocol-di-testing
Protocol-based dependency injection for testable Swift code — mock file system, network, and external APIs using focused protocols and Swift Testing.
web3-testing
Test smart contracts comprehensively using Hardhat and Foundry with unit tests, integration tests, and mainnet forking. Use when testing Solidity contracts, setting up blockchain test suites, or validating DeFi protocols.