memory-optimize

Fail

Audited by Runlayer on Mar 6, 2026

Risk Level: HIGH
Scan Summary
Max Score
90%
Files
3
Flagged
2
Chunks
3
Flagged Files (2)
memory-optimize/SKILL.mdHIGH
90.1%

Risky tool definition detected

Typical reduction: **30–50%** token count in memory files. Auto-memory stores context across sessions in `~/.claude/projects/**/memory/MEMORY.md`. Enable: `CLAUDE_CODE_DISABLE_AUTO_MEMORY=0` · Disable: `CLAUDE_CODE_DISABLE_AUTO_MEMORY=1` **Benefits:** faster context loading · no duplicate rules · cleaner instructions · lower API cost **Usage:** ```bash /memory-optimize # no args — starts 4-step interactive workflow ``` > _Skill text is written for LLM consumption and optimized for token

memory-optimize/README.mdMEDIUM
75.3%

Malicious tool definition detected

- Project rule (this project) --> `.claude/rules/` - Architectural decision --> project `CLAUDE.md` - Reusable fact/pattern --> keep in memory - Session context --> delete (ephemeral) Shows a migration plan with target files and token savings, asks for approval before moving anything.

Passed Files (1)Click to expand
memory-optimize/references/memory-guide.mdOK
15.8%

Tool passed security scan

Audit Metadata
Max File Score
90%
Classification
KNOWN_SERVER_PARTIAL_KNOWN
Files Scanned
3
Files Flagged
2
Chunks Analyzed
3
Analyzed
Mar 6, 2026, 05:27 PM
Security Audit — runlayer — memory-optimize