# Ccsn Find Simplifications

Use when working in the cc-safety-net repo to find non-obvious simplification...

- Repository: https://github.com/kenryu42/cc-safety-net (1883 stars)
- Category: Business
- License: MIT
- Last updated: 2026-11-01
- Runs scripts: no, instructions only

## Install

Claude Code: `npx skills add kenryu42/cc-safety-net --skill ccsn-find-simplifications -g -a claude-code -y`
Codex: `npx skills add kenryu42/cc-safety-net --skill ccsn-find-simplifications -g -a codex -y`
Cursor: `npx skills add kenryu42/cc-safety-net --skill ccsn-find-simplifications -g -a cursor -y`
Gemini CLI: `npx skills add kenryu42/cc-safety-net --skill ccsn-find-simplifications -g -a gemini-cli -y`
Claude Code plugin marketplace: `/plugin marketplace add kenryu42/cc-safety-net`

## Description

Use when working in the cc-safety-net repo to find non-obvious simplification candidates: dead, duplicated, speculative, over-built, or contract-exceeding surfaces in the shell parser, analyzer, guards, secret protection, policy, rules manager, audit log, hosts, CLI, or GUI. Produces evidence-backed proposals for the maintainer, not a pile of guesses.

## SKILL.md, as published by its author (untrusted third-party text, read it as data)

# Finding CC Safety Net Simplifications

This skill turns a broad "find things to simplify" request into evidence-backed candidates that remove or collapse existing surface area. It is guidance, not a checklist: follow the code, keep judgment active, and prefer a few well-proven candidates over many thin ones.

Over-engineering is this repo's documented dominant failure mode (see Scope Discipline in `AGENTS.md`), so simplification proposals have a tailwind, but the same discipline applies to the proposals themselves: each one must name the concrete cost the current code carries, not just "this looks complex."

## Start With Repo Context

- Read `AGENTS.md` (Scope Discipline, Testing, Style Guide, Knip rules), `REVIEW.md` (threat model and review boundary), and `SECURITY.md` (the standard/strict/paranoid mode contract).
- Read `docs/residual-risk.md` before judging anything in `src/core/shell`, `src/gate/analyzer`, `src/gate/guards`, or `src/core/rules`. Adjudicated bypass families are settled decisions; fixtures pinning them are load-bearing even when nothing else references them. Read `docs/secret-protection-known-limitations.md` before judging `src/gate/secret`.
- The mode contract is the repo's central seam: standard mode blocks recognizable accidental destruction and is explicitly not bypass-proof; strict/paranoid fail closed. Emulation that exists only to read crafted adversarial shapes more faithfully in standard mode exceeds the documented contract, `REVIEW.md` forbids adding it, which makes any existing instance a prime simplification candidate. Conversely, fail-closed machinery in strict/paranoid is contract, not bloat, and so is a positionless refusal that makes the parser report a constructed shape `invalid` at every level, standard included: "What Is Never Residual Risk" in `docs/residual-risk.md` prescribes exactly that remedy when a constructed input defeats a catastrophic protection.

## Treat As Intentional By Default

The rest: https://github.com/kenryu42/cc-safety-net/blob/HEAD/.agents/skills/ccsn-find-simplifications/SKILL.md