pathfinder
Maps project code into flowcharts. It identifies duplicated parts and suggests a unified architecture for the system.
What it does
Pathfinder helps you understand how a computer program is organized. It creates diagrams (flowcharts) showing how different parts of the program work together, identifies parts that do the same thing in different places, and suggests a simpler way to organize everything.
When to use it
- ✓When you want to quickly understand complex code.
- ✓When you notice parts of the code are duplicated and want to unify them.
- ✓Before making major changes (refactoring) to a program.
Example of what to ask your AI
“Help me understand the structure of this code and find duplicated parts.”
Want more? Open the sections below.
How to use
The easiest way: copy the message below and paste it into Claude, ChatGPT, Cursor or any AI. It reads the skill and follows the instructions.
Skill link
Ready-to-paste message
How it works
It first divides the program into 'features'. Then, it draws the path each feature follows and looks for duplicated code between them. Finally, it suggests a single, simpler organization and creates instructions for other tools to make action plans.
Installation
Easiest way: copy the skill link and paste it into Claude, ChatGPT or Cursor asking it to follow the instructions.
In the terminal (Claude Code, Codex, Cursor), in your project folder:
npx skills add thedotmack/claude-mem --skill pathfinderOr download just the file:
curl -L https://raw.githubusercontent.com/thedotmack/claude-mem/main/plugin/skills/pathfinder/SKILL.md -o SKILL.mdTechnical content (original SKILL.md)
Original text by the author, straight from GitHub.
Pathfinder
You are an ORCHESTRATOR. Map the codebase into feature-grouped flowcharts, identify duplicated concerns, propose the simplest unified architecture, and hand off per-system plans to /make-plan.
You do not write implementation code. You produce diagrams, a duplication report, a proposed unified flowchart, and handoff prompts.
Delegation Model
Use subagents for discovery and extraction (file reading, flow tracing, grep, diagramming). Keep synthesis (deciding feature boundaries, picking unification strategies, final flowchart) with the orchestrator. Reject subagent reports that lack source citations and redeploy.
Subagent Reporting Contract (MANDATORY)
Each subagent response must include:
- Sources consulted — exact file paths and line ranges read
- Concrete findings — exact function names, call sites, data flow
- Mermaid diagram(s) with nodes labeled by
file:line - Confidence note + known gaps
Output Artifacts
All artifacts go in PATHFINDER-<YYYY-MM-DD>/ at repo root:
00-features.md— feature inventory with boundaries01-flowcharts/<feature>.md— one Mermaid flowchart per feature02-duplication-report.md— cross-cutting duplicated concerns with evidence03-unified-proposal.md— proposed unified architecture + Mermaid04-handoff-prompts.md— copy-pasteable/make-planprompts per unified system
Phases
Phase 0: Feature Discovery (ALWAYS FIRST)
Deploy ONE "Feature Discovery" subagent to:
- Walk the source tree (not built artifacts) and read top-level README / CLAUDE.md
- Propose feature boundaries based on directory structure, import graph, and naming
- Return a flat list of features with: name, entry points (file:line), core files, brief purpose
Orchestrator reviews the proposal, adjusts boundaries if needed, writes 00-features.md. Do NOT fan out until feature boundaries are approved.
Phase 1: Per-Feature Flowcharts (FAN OUT)
Deploy ONE "Flowchart" subagent per feature in parallel. Each receives only its feature's scope. Each must:
- Trace the feature's primary happy path from entry point to terminal state
- Identify side effects (DB writes, HTTP calls, file I/O, process spawns)
- Note error and fallback branches but do not let them dominate the diagram
- Produce a Mermaid
flowchart TDwith every node labeledName<br/>file:line - List external dependencies (other features it calls into) at the bottom
Orchestrator writes each flowchart to 01-flowcharts/<feature>.md. Reject any diagram missing file:line labels.
Phase 2: Duplication Hunt
Deploy TWO subagents in parallel:
"Within-Feature Duplication" subagent:
- For each feature, find repeated code/logic patterns inside the feature only
- Report only duplications worth consolidating (ignore trivial repetition)
"Cross-Feature Duplication" subagent:
- Compare flowcharts across features for concerns that appear in multiple places
- Examples of what to look for: multiple capture paths, parallel queue implementations, duplicated storage/migration code, repeated agent scaffolding, parallel parsing layers
- For each duplication, report: (a) the concern, (b) every location with
file:line, (c) why they diverged, (d) whether the divergence is legitimate specialization or accidental
Orchestrator synthesizes both into 02-duplication-report.md. Every duplication claim must cite ≥2 file:line locations.
Phase 3: Unified Proposal (ORCHESTRATOR)
The orchestrator writes 03-unified-proposal.md itself — do not delegate synthesis.
For each duplicated concern from Phase 2 that is NOT legitimate specialization:
- Propose the simplest unified design (one path, one store, one handler — whatever applies)
- Name the consolidated component and its single entry point
- Show what each old call site becomes
- Call out any loss of capability and whether it's acceptable
End the document with ONE combined Mermaid flowchart showing the proposed unified system. Nodes still labeled with target file:line (new or existing) where knowable.
Anti-patterns to reject in your own proposal:
- Adding a new abstraction layer "for flexibility"
- Keeping both old paths behind a feature flag
- Introducing a registry/factory when a switch statement suffices
- Preserving divergent behavior "just in case"
Phase 4: Per-System Handoff Prompts
For each unified system in the proposal, write a ready-to-run /make-plan prompt to 04-handoff-prompts.md. Each prompt must:
…
FAQ
What are 'flowcharts'?
They are diagrams that show the workflow or sequence of steps in a process or program.
What does 'unify architecture' mean?
It means finding a simpler and more organized way to handle tasks that are being done in repetitive or complicated ways across different parts of the program.
Does Pathfinder write the code to fix the program?
No, it only analyzes existing code, identifies problems, and creates plans (instructions) for other tools to make the fixes.
Details
Original description by the author
Map a codebase into feature-grouped flowcharts, identify duplicated concerns across features, and propose a unified architecture. Use when asked to "find the ideal path," unify duplicated systems, or audit architecture before a refactor. Emits a proposed unified flowchart plus per-system /make-plan prompts.
repo: thedotmack/claude-mem
Popularity
- GitHub stars
- 101k
- Ranking position
- #817
- License
- Apache-2.0
- Updated
- 10/16/2026
Comments
- …
More skills from this repository
Agent Cost Report
Has your agent generate detailed cost reports for its activities. Shows how much was spent on tokens and services.
thedotmack/claude-mem
claude-mem-install
Helps your agent set up Claude-Mem in different environments. Allows choosing between local or remote workers and configuring observation.
thedotmack/claude-mem
mem-search
Lets your agent search past memories. Useful for recalling previous solutions or work from old sessions.
thedotmack/claude-mem
host-observer
Helps your agent respond to Claude-Mem observer tasks. It should only reply with 'skip_summary' or a full XML observation.
thedotmack/claude-mem
Similar skills
bun-runtime
Has your agent use Bun to run, organize, and test code. It helps choose Bun over other tools and migrate existing projects.
affaan-m/ECC
database-migrations
Helps your agent make safe changes to databases. It ensures changes can be undone and minimizes downtime.
affaan-m/ECC
deployment-patterns
Sets up deployment and CI/CD workflows, containerization, and rollback strategies to ensure safe releases.
affaan-m/ECC