AI Skill MartBrowse skillsPromptsProgramsLearnWhat is a Skill?
 
← Back to list

Pathfinder (Unified Architecture Mapper)

Maps a codebase into feature-grouped Mermaid flowcharts, hunts duplicated concerns with file:line evidence, and proposes the simplest unified architecture before a refactor.

Dev & CodingAdvanced★ 90,139⑂ 7,846AI score 8/10Last updated: Aug 9, 2026

What it does

  • Feature discovery: walks the source tree and import graph to produce a feature inventory (00-features.md) with entry points and core files.
  • Per-feature flowcharts: traces each feature's happy path end to end and emits a Mermaid flowchart TD where every node is labeled file:line.
  • Duplication report: finds within-feature and cross-feature duplication (multiple capture paths, parallel queues, repeated storage/migration code) and requires at least two file:line citations per claim.
  • Unified proposal: picks the simplest consolidation (one path, one store, one handler), shows what each old call site becomes, and explicitly rejects anti-patterns like new abstraction layers, feature-flagged dual paths, or registries where a switch would do.
  • Handoff prompts: writes copy-pasteable /make-plan prompts per unified system.

Everything lands in a PATHFINDER-<date>/ folder at repo root. The skill itself never writes implementation code.

Who it's for

  • Developers and tech leads documenting current architecture before a large refactor
  • Teams cleaning up codebases where similar features were implemented multiple times
  • Engineers onboarding to an unfamiliar repo who want diagrams of the real flows
  • Anyone preparing an architecture audit or tech-debt review

Examples

  1. "Find the ideal path in this repo" → approve feature boundaries, then receive per-feature flowcharts, a duplication report, and a unified proposal.
  2. "We seem to have three capture pipelines — can they be merged?" → get a duplication report citing each path's file:line plus a single-entry-point consolidation design.
  3. "Audit the architecture before we refactor" → get documents that separate current state (Phases 0–2) from target state (Phase 3), plus ready-to-run /make-plan prompts.

· · · Install guide · · ·

Try it now, no install

Paste this into Claude to use the skill without installing anything.

Read the instructions in this file and follow them to help me:
https://raw.githubusercontent.com/thedotmack/claude-mem/HEAD/plugin/skills/pathfinder/SKILL.md

What I want: (describe your task here)

If Claude can't open the link, open it yourself and paste the contents instead.

↓ If it works for you, download the ZIP below and install it. Then it runs on its own — no pasting each time.

Install in the Claude app (no terminal)
  1. Download the ZIP with the button below.
  2. In Claude, open Settings → Capabilities and turn on 'Code execution and file creation'. (one time)
  3. Go to Customize → Skills → + → 'Upload a skill' and upload the ZIP.
↓ Download ZIP
Install in Claude Code

Let Claude do it — paste this into Claude Code

Install the skill I found on AI Skill Mart.
Copy the plugin/skills/pathfinder folder from the GitHub repo thedotmack/claude-mem into my ~/.claude/skills/pathfinder/.
When it's done, tell me in one line what this skill can do.

Install with a command instead

git clone https://github.com/thedotmack/claude-mem.git && mkdir -p ~/.claude/skills && cp -r claude-mem/plugin/skills/pathfinder ~/.claude/skills/

⚠ This is a third-party skill. Check the source repository before installing.

  1. Open a terminal and clone the repo: git clone https://github.com/thedotmack/claude-mem.git
  2. Create the skills directory if needed: mkdir -p ~/.claude/skills
  3. Copy the skill: cp -r claude-mem/plugin/skills/pathfinder ~/.claude/skills/
  4. Verify that ~/.claude/skills/pathfinder/SKILL.md exists.
  5. Restart Claude Code and open the project you want to analyze.
  6. Trigger it with a request like "use pathfinder to find the ideal path in this codebase".
  7. To use the handoff steps (/make-plan, /do), install the full claude-mem plugin as well.
  8. Expect high token usage — the workflow fans out several subagents in parallel.
View source on GitHub ↗License: Apache-2.0