Memory Self Review — Security skill for Claude Code
Mine recent agent history (claude-mem + usage stats) for recurring failures and repeated patterns, audit MEMORY.md health, and PROPOSE (never apply) CLAUDE.md/memory edits for human approval.
How to install Memory Self Review
Installs to ~/.claude/commands/ucsandman-dashclaw-memory-self-review.md
mkdir -p ~/.claude/commands && curl -fsSL https://raw.githubusercontent.com/ucsandman/DashClaw/HEAD/.claude/commands/memory-self-review.md -o ~/.claude/commands/ucsandman-dashclaw-memory-self-review.md Restart Claude Code, or start a new session, for it to be picked up.
What Memory Self Review does
description: Mine recent agent history (claude-mem + usage stats) for recurring failures and repeated patterns, audit MEMORY.md health, and PROPOSE (never apply) CLAUDE.md/memory edits for human approval. argument-hint: "[days, default 7]" model: sonnet
You are running DashClaw's **self-improvement loop**. Your job is to turn the last $1 (default 7) days of agent history into a small, concrete set of PROPOSED improvements to the operator's persistent instructions and memory. This is **h
Alternatives in Security
- Coding Audit — Medical-coding / revenue-cycle compliance audit 83 ★
- Karpenter — Design, install, debug, review, plan capacity, audit scaling history, migrate from Cluster Autoscaler, and upg 40 ★
- Generalise — Audit a lemma or definition for assumption-weakening opportunities — try mechanical weakenings, search the lit 33 ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Flake Audit
Detect intermittently-failing tests from recent CI history (or repeated local runs); dedupe against tracked fl
Skills Suggest
Audit recent sessions for repeated tasks and AI-output-then-manual-verification patterns. Produces a ranked li
Gaia Harden
Judge-the-form, human-gated hardening. Reviews recurring code-audit-frontend findings and, with approval, draf
Audit Quiz Coverage
Find quiz coverage gaps from recent guide/CHANGELOG/CC-releases changes and propose new questions
Security Watch
One security-watch pass over an EVM / Solidity repo — deps + static analysis + risky-pattern grep + recent adv
Open Skills
The improve- family: senior-advisor Claude Code skills that audit a codebase (copy, prompts, error handling, a
Related Agents
History Analyst
Analyzes git history for changed files to surface context: recent refactors, reverted changes, repeated bug fi
Stats Analyzer
Analyzes ~/.claude/stats-cache.json and history.jsonl to produce a concise usage report with model token break
Post Debugger
Diagnoses failed Upload-Post uploads, expired social tokens, scheduling errors, and AutoDM monitor failures. R