progressive-disclosure

A guide to choosing how many KiCad MCP Pro tools an AI agent can use at once. Profiles are preset tool groups for review, building, manufacturing release, or expert work.

In plain words
What is it for?
It helps configure read-only reviews, controlled design changes, manufacturing validation, or access to the complete expert tool catalog.
Why use it?
It keeps ordinary agents focused and limits risky operations unless broader access is deliberately enabled.

Agent

Install

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.

agentmods
npx agentmods add agents/oaslananka/kicad-mcp-pro/progressive-disclosure
Clone the repo
git clone --depth 1 https://github.com/oaslananka/kicad-mcp-pro
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 877 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.00877
Opus 5 $0.00000 $0.00439
Sonnet 5 $0.00000 $0.00175
Haiku 4.5 $0.00000 $0.00088

Measured yesterday against content hash c8ca91c74ff8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

progressive-disclosure 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 yesterday.

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.

docs/agents/progressive-disclosure.md · 75 lines

How it starts

The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Progressive-Disclosure Profiles

KiCad MCP Pro defaults to a bounded tool surface so general-purpose agents do not need to choose from the complete expert catalog.

Workflow profiles

Profile Operating mode Callable tools Intended use
default readonly 24 Safe general-agent review and next-action discovery
review readonly 24 Explicit read-only DRC, ERC, DFM, visual QA, and component-contract review
build write 24 Plan/apply/verify workflows plus bounded PCB inspect/remove/DRC operations
release manufacturing 24 Validation and human-gated manufacturing package generation
expert experimental 377 Complete catalog for trusted advanced clients

full and agent_full remain available for backward compatibility. They expose the complete catalog and should not be the default for a general agent.

Review is the safe default:

KICAD_MCP_PROFILE=default
KICAD_MCP_OPERATING_MODE=readonly

Controlled source editing requires both the build profile and write mode:

KICAD_MCP_PROFILE=build
KICAD_MCP_OPERATING_MODE=write

Manufacturing handoff requires both the release profile and manufacturing mode:

KICAD_MCP_PROFILE=release
KICAD_MCP_OPERATING_MODE=manufacturing

The profile controls discovery. The operating mode is an independent execution-risk gate. Selecting build while remaining in readonly mode does not silently enable write operations. Selecting release without manufacturing mode does not expose the final package operation.

Safety boundaries

The review profile contains only READ-tier capabilities. The eight review-profile-tagged golden cases retain 100% expected-tool coverage while exposing none of the destructive tools explicitly forbidden by those cases. The broader tool-selection corpus also covers build, mutation, export, publish, confirmation, and refusal behavior and is not expected to fit inside the review surface. Category discovery is profile-aware: hidden categories and lower-level tool names are not returned by the discovery tools until the server starts with a profile that allows them.

Read the full file on GitHub · 75 lines

Changes

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.

  1. yesterday First seen · 75 lines · 0 tokens per session scan A c8ca91c74ff8

Subscribe to this mod's changes

progressive-disclosure is an agent published in the GitHub repository oaslananka/kicad-mcp-pro (62 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 877 tokens. 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.