Claude skill
Pathfinder
Pathfinder is a Claude skill in the Claude Mem plugin. Map a codebase into feature-grouped flowcharts, identify duplicated concerns across features, and propose a unified architecture.
What it does
The description in the skill's SKILL.md, which Claude reads to decide when to use it:
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.
The skill's instructions (about 827 words) cover:
- Delegation Model
- Subagent Reporting Contract (MANDATORY)
- Output Artifacts
- Phases
- Phase 0: Feature Discovery (ALWAYS FIRST)
- Phase 1: Per-Feature Flowcharts (FAN OUT)
- Phase 2: Duplication Hunt
- Phase 3: Unified Proposal (ORCHESTRATOR)
- Phase 4: Per-System Handoff Prompts
- Key Principles
- Failure Modes to Prevent
How to use it
- Pathfinder comes inside the Claude Mem plugin, so you get it by installing that plugin, along with its 31 other skills. A plugin installs as one unit, with all its skills. The plugin's page has the install steps, and plugins are saved to your Claude account.
- Ask Claude for the task. When your request matches the skill's description, Claude loads it.
- To pick it yourself in Claude chat, type
/or click + and choose pathfinder. In Claude Code and Cowork, type:/claude-mem:pathfinder
Source
- Plugin
- Claude Mem
- SKILL.md
- View on GitHub
- Repo stars
- 117,521
- Repo last pushed
- Nov 16, 2026
- Checked
- Nov 16, 2026
More skills in Claude Mem
- ReleaseFully automate a release with version-bump and childhood.
- Request ProgressGroup recent conversations into overall requests, review each one's progress from memory, sort each into one of the owner's focus areas, and write the build story, so My Work shows progress meters…
- ScreenpipeSearch screen and audio history recorded by Screenpipe and optionally save selected context into claude-mem.
- Smart ExploreToken-optimized structural code search using tree-sitter AST parsing. Use instead of reading full files when you need to understand code structure, find functions, or explore a codebase efficiently.
- StandupFacilitate a read-only standup across git worktrees, branches, or PRs to compare changes and produce one consolidation plan.
- Timeline ReportGenerate a "Journey Into [Project]" narrative report analyzing a project's entire development history from claude-mem's timeline.
- Version BumpMaintainer release workflow for the thedotmack/claude-mem repository only.
- Weekly DigestsGenerate a serial week-by-week narrative digest of a project's full claude-mem timeline.
- What theWhat the? Use when the user wants a plain-English breakdown of something technical — the who, what, where, why, and when.
- WowerpointTurn one document into a kawaii NotebookLM slide deck.
- Agent Cost ReportBelievable agent cost report for any period, default the last 7 full days PT, not counting today.
- BabysitWatch a pull request or review cycle until it is ready to merge. Use when asked to babysit, monitor, or keep checking PR comments, reviews, and CI until all actionable issues are resolved.
- Backup SetupSet up, check, or restore local claude-mem database snapshots. Use when the user says "set up backups", "back up my memories", "backup status", or "restore my database".
- Build and ReleaseFully automate building and releasing a coding task.
- Ccs AlignRun the CCS Align seat's hourly breathing cycle — prove the local claude-mem worker is healthy, pull needle observations through search → timeline → get_observations, land them in a seat-owned…
- ChildhoodBabysit a shipped release after merge, publication, or deployment.
- Claude Mem InstallUse this when setting up claude-mem on Cursor: local or remote worker, local host-login observer or remote cmem.ai inference.
- Cloud SyncSet up or check claude-mem cloud sync with cmem.ai Pro.
- Design IsAudit a design against Dieter Rams' ten "Good design is..." principles, then hand off a /make-plan prompt for one of three outcomes — new design, refine design, or redesign.
- DoExecute a phased implementation plan using subagents. Use when asked to execute, run, or carry out a plan — especially one created by make-plan.
- HandoffGenerate a HANDOFF.md that captures goal, current state, files touched, failed attempts, and next steps — so a fresh Claude session can continue exactly where this one left off.
- Host ObserverUse this when fulfilling claude-mem observer jobs on Grok Bot: reply only skip_summary or one full observation XML, never prose.
- How It WorksExplain how claude-mem captures observations, when memory injection kicks in, and where data lives. Use when the user asks "how does claude-mem work?" or "what is this thing doing?".
- Knowledge AgentBuild and query AI-powered knowledge bases from claude-mem observations.