Why — multi-source design-rationale investigations (short pointer)
Answer "why does this code exist" with parallel investigator agents over git, tickets, docs, chat, observability, errors and analytics — short pointer
- What
- Answer "why does this code exist" with parallel investigator agents over git, tickets, docs, chat, observability, errors and analytics — short pointer
- Cost
- Free
- Needs
- an agent environment with subagents and MCP access (the workflow is written for Cursor — adapt the orchestration to your harness); licensed under MIT (Copyright (c) 2026 Lauren Tan) — read it yourself before reusing its content
- Install
- Copy the installer prompt below into your Muse — your agent does the rest.
Curated by Skill Harbor — a short pointer to @cursor's why skill: a rigorous methodology for answering "why does this code work this way" instead of "what does it do". The workflow anchors the investigation in concrete code (blame, log, PR numbers), then spawns parallel investigator agents — one per evidence category: source control, issue tracker, long-form docs, team chat, infrastructure observability, error tracking, product analytics warehouse — over the MCPs available in the environment, and synthesizes the findings under a strict epistemics framework (what we know, what we infer, competing hypotheses, what we don't know, one line per source consulted). Honest caveats: licensed under MIT (Copyright (c) 2026 Lauren Tan); this is a short fiche linking to the source, without reusing its content; it is built for Cursor's environment (MCP discovery, Task subagents, `pstack-models.mdc` model slugs) — adapt the orchestration to your own agent harness; expect heavy compute on wide sweeps. Skill Harbor never reviews the code, review it yourself before use. Discovered via skills.sh.
Version:
Quick answer
Why is a free short pointer to a rigorous methodology for answering why code works this way, instead of what it does. The workflow anchors the investigation in concrete code with blame, log and PR numbers, then spawns parallel investigator agents, one per evidence category, over git, tickets, docs, chat, observability, errors and analytics, to build the design rationale.
Install
Copy the install package below, then paste it into Muse🧪 Install ran in our test sandbox · Nov 18, 2026📌 Pinned version: commit ccb5507Step 0 — before installing anything: read this install prompt, summarize in a few lines what this build does and what installing it involves, then ask me to confirm before you proceed. Prerequisites: an agent environment with subagents and MCP access (the workflow is written for Cursor — adapt the orchestration to your harness); licensed under MIT (Copyright (c) 2026 Lauren Tan) — read it yourself before reusing its content Install "Why — multi-source design-rationale investigations (short pointer)" for me. Fetch the SKILL.md from the source repository into a temporary folder, review it for anything suspicious, and report in two or three sentences what the why workflow covers (code anchoring, parallel per-category investigators, epistemics-framed synthesis) so I can adapt it to my own agent setup. Do not copy the workflow's content into my project — this is a reference lookup only. Repository: https://raw.githubusercontent.com/cursor/plugins/ccb5507cec1546dc88135c1139c811e6c59115ba/pstack/skills/why/SKILL.md Pinned version: install the code at commit ccb5507cec1546dc88135c1139c811e6c59115ba exactly (Skill Harbor tested this version). Do not substitute a newer version. If this commit is unreachable, stop and tell me. GitHub is optional: if I have a GitHub account or the gh CLI, you may use it; otherwise public access is fine. Rules: don't touch anything outside the temp folder. If anything looks off, stop and ask me. Correction (November 15, 2026): the old prompt said no license was declared in the source repo. That was wrong: pstack/LICENSE at the pinned commit is the MIT License, Copyright (c) 2026 Lauren Tan, and the repository README at the same commit states the license is MIT. Only the license sentence above was corrected; nothing else in this prompt changed.
Saved to your recent installs. Find it anytime on /connect.
🔒 Security, provenance and what this touches
The install prompt below already includes the vetting steps: your agent follows the community checklist before installing anything with executable code. Want more?
Verification certificate
Dated facts about what was checked for this listing, and how. This is not a safety certification.
- Pinned version
- ccb5507 · 2026-10-13
- Sandbox install test
- Install ran in our test sandbox · Nov 18, 2026 · Observed during the install test: registry.npmjs.org
- Creator identity
- Not verified
- Fingerprint watch
- Last checked · Nov 19, 2026 : no change detected in the files linked by this install prompt
- Install prompt analysis
- 2026-10-13 : No commands, network calls, packages, file writes or API keys detected.
Skill Harbor never reviews the code of a listed skill. These are dated facts about the install prompt and our install test, not a safety certification. Review a skill yourself before you install it. How we verify
Questions
How do I install a skill?
Every product page includes a copy-paste install prompt. Paste it into your Muse and it sets the skill up for you — no manual configuration.
Where does my money go?
Straight to the seller. Skill Harbor never processes payments: checkout happens on the seller’s own page, usually Stripe.
What does the ✓ next to a creator’s name mean?
It means we confirmed the identity of the person behind the listing. It says nothing about the code itself — always check a skill before installing it.