heznpc

12 mods across 2 repositories, 16 stars between them.

airmcp

01

heznpc/AirMCP

Plugin Claude Code

Governed MCP runtime for the Apple ecosystem and the connector layer between AI clients and Apple apps. The macOS runtime is available today and the iOS runtime is in preview, with visionOS and watchOS as roadmap targets. Profiles and progressive discovery keep the client surface focused; HMAC-chained audit logs…

16 today A tokens not measured original MIT

review

02

heznpc/AirMCP

Command Claude Code

Stratified code review routed by risk tier (RFC 0013/0014) — not a flat scan.

16 today A 23 tokens original MIT

airmcp

03

heznpc/AirMCP

MCP server Claude CodeCodexCursor +2

Governed MCP runtime for the Apple ecosystem, available on macOS for Notes, Mail, Calendar, Reminders, Shortcuts, and more. Runs locally from the airmcp npm package.

16 today A tokens not measured original MIT

architecture

04

heznpc/PLOIDY

Command Claude Code

Evaluate an architecture proposal — deep-context take (full system) vs first-principles (proposal only) — to catch sunk-cost rationalisation before the change lands.

0 5d ago A 33 tokens original MIT

deprecate

05

heznpc/PLOIDY

Command Claude Code

Pressure-test a deprecation decision — builder's view (knows why it exists, who depends on it) vs cold reader (just sees the thing and the question "should this go?") — to catch attachment-driven maintenance.

0 5d ago A 46 tokens original MIT

hiring

06

heznpc/PLOIDY

Command Claude Code

Hiring decision second opinion — manager's view (full résumé + interview context + team fit) vs identity-blind qualifications-only view — to catch familiarity / pedigree bias in candidate evaluation.

0 5d ago A 36 tokens original MIT

ploidy

07

heznpc/PLOIDY

Command Claude Code

Run a context-asymmetric debate on the current question — Deep (full project context) vs Fresh (zero context) — and return the convergence result.

0 5d ago A 30 tokens original MIT

post-mortem

08

heznpc/PLOIDY

Command Claude Code

Run a Ploidy debate on a post-mortem — context-rich account (knows history, people, prior judgements) vs timeline-only reader — to surface blame anchoring and unexplored root causes.

0 5d ago A 43 tokens original MIT

product-decision

09

heznpc/PLOIDY

Command Claude Code

Evaluate a product decision — maker's view (knows users, history, constraints) vs first-time-reader view (spec only) — to catch sunk-cost feature bias and "because we always do it this way" product choices.

0 5d ago A 46 tokens original MIT

review-pr

10

heznpc/PLOIDY

Command Claude Code

Run a Ploidy debate on a pull request — deep-context reviewer vs zero-context reviewer that sees only the diff + description — to catch over-engineering, scope creep, and rationalised author bias before merge.

0 5d ago A 43 tokens original MIT

spike

11

heznpc/PLOIDY

Command Claude Code

Sanity-check a design idea BEFORE implementation — runs a Ploidy debate between the full-context view and a zero-context fresh sub-agent to surface rationalisation before code gets written.

0 5d ago A 36 tokens original MIT

ploidy

12

heznpc/PLOIDY

MCP server Claude CodeCodexCursor +2

MCP server "ploidy" as configured in heznpc/PLOIDY. Runs ploidy with python3.

0 5d ago A tokens not measured original MIT