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 agents/oaslananka/kicad-studio-kit/codex-supportgit clone --depth 1 https://github.com/oaslananka/kicad-studio-kitWrote 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/oaslananka/kicad-studio-kit/codex-support)<a href="https://agentmods.dev/agents/oaslananka/kicad-studio-kit/codex-support"><img src="https://agentmods.dev/badge/agents/oaslananka/kicad-studio-kit/codex-support.svg" alt="Measured on agentmods" 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 | $0.00000 | $0.00394 |
| Opus 5 | $0.00000 | $0.00197 |
| Sonnet 5 | $0.00000 | $0.00079 |
| Haiku 4.5 | $0.00000 | $0.00039 |
Grade B, and why
codex-support scanned grade B 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
Use `examples/mcp-clients/codex.config.example.toml` as the `~/.codex/config.toml` What it actually says
Codex Support
KiCad Studio Kit supports Codex through the external MCP client path.
Extension Provider Status
kicadstudio.ai.provider=codex is a legacy setting value, not a current direct KiCad
Studio extension provider. KiCad Studio migrates that legacy value to copilot because the
old implementation used the VS Code Language Model API and Copilot-compatible models.
Related implementation and docs:
apps/vscode-extension/src/ai/aiProvider.tsapps/vscode-extension/src/settings/settingsMigrations.tsapps/vscode-extension/docs/AI_PROVIDERS.mddocs/extension/settings.md
External Codex MCP Client
OpenAI Codex CLI and Codex IDE extension can connect to kicad-mcp-pro as MCP clients.
Use examples/mcp-clients/codex.config.example.toml as the ~/.codex/config.toml
starting point, or use the CLI form below:
codex mcp add kicad \
--env KICAD_MCP_PROJECT_DIR=/absolute/path/to/your/kicad-project \
--env KICAD_MCP_PROFILE=pcb_only \
--env KICAD_MCP_OPERATING_MODE=readonly \
-- uvx kicad-mcp-pro
This external-client path gives Codex access to KiCad MCP tools. It is separate from the VS Code extension's direct AI provider setting.
Rule Of Thumb
- Use
kicadstudio.ai.provider=copilotwhen you want KiCad Studio's chat UI to route through the VS Code Language Model API. - Use Codex MCP config when Codex is the coding agent or IDE agent connecting to
kicad-mcp-pro. - Do not describe the extension provider setting as the Codex CLI integration.
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 · 42 lines · 0 tokens per session scan B b5a76a3d57ed
codex-support is an agent published in the GitHub repository oaslananka/kicad-studio-kit (15 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 394 tokens. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other agents, from other repositories
chatgpt-app
KiCad MCP Pro has one verified ChatGPT-facing profile today: a public-safe, read-only Streamable HTTP app. It can analyze repository-owned or uploaded project data inside an explicitly configured upload root and render three HTML widgets. It does not grant ChatGPT direct access to a user's local KiCad process.
index
Agent "index" from oaslananka/kicad-mcp-pro, covering kicad mcp — ai agent integration guide, supported agents, quick start, install and run diagnostics.
progressive-disclosure
KiCad MCP Pro defaults to a bounded tool surface so general-purpose agents do not need to choose from the complete expert catalog.
toolsets
KiCad MCP has a 377-tool expert catalog. General agents should use the bounded workflow toolsets below instead of loading the complete catalog.
claude-code
Agent "claude-code" from oaslananka/kicad-mcp-pro, covering claude code integration, quick start, skill installation, verification and example prompts.
cline
Cline is an autonomous coding agent for VS Code (and a CLI). It speaks MCP over stdio and HTTP.