project-memory
A local “memory” skill for Claude Code that bootstraps and maintains a standardized set of project documentation files (bugs, decisions/ADRs, key facts, and an issues/work log) plus memory-aware protocol sections in CLAUDE.md/AGENTS.md to help agents maintain continuity across sessions.
Score Breakdown
⚙ Agent Friendliness
🔒 Security
Strong guidance in README: key_facts.md should not contain passwords/API keys/credentials, and sensitive data should be stored in .env or secret managers. However, the package appears file-based and its enforcement/guardrails against accidental secret inclusion are not described. No TLS/auth controls apply because no service/API is mentioned.
⚡ Reliability
Best When
You want agent assistance to follow consistent project documentation patterns and you’re comfortable with a file-based, repo-local workflow.
Avoid When
You need centralized, authenticated, multi-user memory retrieval or strong compliance/audit controls beyond what git-tracked files provide.
Use Cases
- • Keeping a structured bug log with root causes, solutions, and prevention notes
- • Recording architectural decisions (ADRs) and linking them to subsequent work
- • Maintaining project configuration references (non-secret) for faster agent onboarding
- • Logging completed work/tickets to preserve context across coding sessions
- • Standardizing institutional knowledge for teams using multiple AI coding tools
Not For
- • Storing or managing actual secrets/credentials
- • Providing a centralized remote memory service with search/query APIs
- • Use as an enterprise knowledge base with access controls/auditing
- • Automating deployment/runtime operations through an external service
Interface
Authentication
The README describes a local skill that creates/updates documentation files in a project directory; no network authentication or user authorization mechanism is described.
Pricing
License badge indicates MIT, and no pricing model is described for the skill itself. Costs would come indirectly from your coding agent usage, not from this package.
Agent Metadata
Known Gotchas
- ⚠ Key facts file is intended to store only non-sensitive references; agents may accidentally add secrets unless users enforce review/gitleaks scanning.
- ⚠ File-based memory can grow over time; without manual cleanup, search relevance may degrade.
- ⚠ Skill behavior depends on Claude Code’s handling of CLAUDE.md/AGENTS.md protocols; other agents may not fully honor the same conventions.
Alternatives
Full Evaluation Report
Comprehensive deep-dive: security analysis, reliability audit, agent experience review, cost modeling, competitive positioning, and improvement roadmap for project-memory.
AI-powered analysis · PDF + markdown · Delivered within 30 minutes
Package Brief
Quick verdict, integration guide, cost projections, gotchas with workarounds, and alternatives comparison.
Delivered within 10 minutes
Score Monitoring
Get alerted when this package's AF, security, or reliability scores change significantly. Stay ahead of regressions.
Continuous monitoring
Scores are editorial opinions as of 2026-03-30.