Why is this code like this - a git-log chain over one file[:line], joined to the phase, task, decision, deviation and review record on disk
Scanned 9/3/2026
Install to Claude Code
npx -y skills add crenshawdev/cadence --skill cad-why --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Cad Why?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/crenshawdev-cad-why)More formats (shields.io, HTML) on the badges page.
---
name: cad-why
description: "Why is this code like this - a git-log chain over one file[:line], joined to the phase, task, decision, deviation and review record on disk"
argument-hint: "<path>[:<line>]"
allowed-tools:
- Bash
---
<objective>
Answer "why is this code like this" from the record already on disk, at one
file and line. Read-only: no write, no dispatch, no summarization - the seam
does the whole join and this skill relays what it returns.
</objective>
<process>
1. Run the seam with the query as ONE single-quoted literal word:
`node "${CLAUDE_PLUGIN_ROOT}/cadence-core/bin/why.mjs" '<path>[:<line>]' --dir .`
Single quotes, never double: `$ARGUMENTS` is caller-supplied, and a
double-quoted `$(...)` or backtick inside it runs before Node starts. A
query containing a single quote is refused here, never escaped. Parse the
one JSON line it prints.
2. `ok:false` - state the `reason` and `detail` fields plainly and stop.
3. `ok:true` - print the `text` field VERBATIM and nothing else: no summary
before it, no commentary after it, no reformatting. `text` is already the
whole answer, quoted from the record in its own words - reformatting it
here would make the byte-identity a reader can check against the seam's
own output false.
</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', ...
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.
**Complete production-ready guide for Google Gemini embeddings API** This skill provides comprehensive coverage of the `gemini-embedding-001` model for generating text embeddings, including SDK usage, REST API patterns, batch processing, RAG integration with Cloudflare Vectorize, and advanced use cases like semantic search and document clustering. ---
Recovers prior coding-agent session context by running `catchup <agent> --since-compact`, which extracts a clean summary of a previous Codex, Claude Code, Antigravity, OpenCode, or Pi Agent session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", or asks to recover/summarize a previous session before continuing. Do NOT use for the current conversation, git history, or any non-agent log.