Gather phase context before planning - codebase assumptions, locked decisions, falsifiable acceptance criteria - in one pass
Scanned 9/3/2026
Install to Claude Code
npx -y skills add crenshawdev/cadence --skill cad-context --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Cad Context?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/crenshawdev-cad-context)More formats (shields.io, HTML) on the badges page.
---
name: cad-context
description: "Gather phase context before planning - codebase assumptions, locked decisions, falsifiable acceptance criteria - in one pass"
argument-hint: "[phase number]"
allowed-tools:
- Read
- Write
- Edit
- Bash
- Grep
- Glob
- AskUserQuestion
- Task
---
<objective>
Run the single pre-plan gate for a phase: spawn the assumptions analyzer
against the codebase when this phase buys that pass, close the gray areas it
surfaces with a few targeted questions, and lock falsifiable acceptance
criteria. Two asks, never merged into one: one spend question (is the analyzer
pass worth buying here?) before it runs, and one size question (too big for one
plan?) after the criteria. Writes `.planning/phases/<N>/CONTEXT.md` for
/cad-plan to read. Optional - /cad-plan runs without it.
</objective>
<execution_context>
@${CLAUDE_PLUGIN_ROOT}/cadence-core/workflows/context.md
</execution_context>
<process>
Execute end-to-end.
</process>
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...