mcpField
C
claude-code-project-memory

claude-code-project-memory

github.com/vasilyu1983Agent workflows44 installs
Repository

About claude-code-project-memory

A guidance skill for configuring Claude Code project memory with `CLAUDE.md` and scoped rule files. It covers memory loading, imports, cross-assistant file strategies, and validation to keep project instructions organized across sessions.

Key features

  1. 01Organize project and user memory
  2. 02Split guidance into scoped rule files
  3. 03Load additional context with imports
  4. 04Mirror memory files across assistants
  5. 05Lint and review memory changes

Use cases

  1. 01Set up shared instructions for a repository
  2. 02Scope testing or security rules to paths
  3. 03Maintain memory across coding assistants

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/vasilyu1983/ai-agents-public --skill claude-code-project-memory

After installing, type/claude-code-project-memoryin Claude Code to confirm it loaded.

Details

From the project README

Claude Code Project Memory (Jan 2026)

Configure CLAUDE.md project memory so Claude Code gets stable, scoped instructions across sessions while keeping token cost low.

Quick Reference

Memory TypeTypical LocationPurpose
Managed policyOS-dependent (see official docs)Organization-wide standards (security, compliance)
Project memory./CLAUDE.md or ./.claude/CLAUDE.mdShared project context and conventions
Project rules./.claude/rules/*.mdModular, topic-focused rules (testing, security, style)
User memory~/.claude/CLAUDE.mdPersonal preferences across projects
Project memory (local)./CLAUDE.local.md (git-ignored)Local-only, project-specific preferences
How Loading Works (High Level)
  • Recursive loading: from the current working directory up to (but not including) filesystem root (/).
  • On-demand loading: nested CLAUDE.md files under the cwd are loaded only when Claude reads files in those subtrees.
  • Imports: @path/to/file pulls in additional context (max depth: 5; ~ supported).

Workflow (Best Practice)

  1. Start with a minimal CLAUDE.md (50–120 lines): what the project is, how it’s shaped, and the “must not break” rules.
  2. Move long or fragile guidance into .claude/rules/ (one topic per file).
  3. Use @imports as navigation for detailed docs instead of copying them into memory.
  4. Treat memory like code: PR review, ownership, and periodic cleanup (remove dead rules).

Rules With Optional Path Scope

Create .claude/rules/testing.md, .claude/rules/security.md, etc. If a rule only applies to a slice of the repo, scope it:

---
paths:
  - "src/api/**/*.ts"
---

Commands (Claude Code)

  • > /memory to view and directly edit memories.
  • > /init to bootstrap project memory (see official docs for current behavior).

Cross-Platform Strategy (AGENTS.md + CLAUDE.md)

If you support multiple coding assistants, keep one canonical file and mirror it:

  • macOS/Linux: symlink one to the other.
  • Windows: prefer copying (or a small sync script) over symlinks unless Developer Mode is enabled.

Avoid tool-specific claims in the memory file; keep it portable and strictly project-focused.

Validation (Fast Checks)

  • Run the bundled linter: bash frameworks/shared-skills/skills/claude-code-project-memory/scripts/lint_claude_memory.sh .
  • Manually scan for unresolved @imports and secrets before merging memory changes.

Resources

ResourcePurpose
references/memory-patterns.mdPatterns and anti-patterns
references/memory-examples.mdFull examples by stack
references/large-codebase-strategy.md100K–1M LOC strategy
data/sources.jsonOfficial links

Related Skills

SkillPurpose
claude-code-skillsSkill creation patterns
claude-code-agentsClaude Code agent setup
docs-codebaseRepo documentation patterns

Comments

Markdown supported