Skip to content

stark-ai-de/agent-skills / skills/claude-operations/claude-memory-curator

claude-memory-curator

Verified

Audit and safely curate Claude Code instructions, rules, auto memory, and memory settings. Use when reviewing stale or misplaced Claude Code context, not Claude app memory or API memory stores.

references/example-review-report.md

View on GitHub
# Example Claude Memory Review

Selected workflow: `review-chat`. This example creates no durable curation report.

## Top Decisions

1. Move the API-specific guidance from broad `CLAUDE.md` into a path-scoped `.claude/rules/api.md`.
2. Delete stale auto-memory notes about the old `npm test` command because `package.json` proves the command changed.
3. Recommend a PreToolUse hook for the "never deploy production" rule because instruction text is not enforcement.

## Summary

- Claude context files inspected: 5
- Entries extracted: 7
- Keep: 1
- Rewrite: 1
- Move to Claude rule: 1
- Move to auto memory topic: 1
- Move to settings: 1
- Move to hook: 1
- Delete: 1
- Ask user: 0

## Highest-Risk Context

| ID  | Source                    | Risk       | Recommendation                                  |
| --- | ------------------------- | ---------- | ----------------------------------------------- |
| C-2 | `~/.claude/.../MEMORY.md` | stale      | Delete old command after backup and approval.   |
| C-4 | `CLAUDE.md`               | unenforced | Move hard restriction to a hook recommendation. |
| C-6 | `.claude/rules/deploy.md` | sensitive  | Remove redacted token-like value and rotate it. |

## Proposed Cleanup Table

| ID  | Current claim              | Classification        | Risk tags  | Confidence | Reason                         | Proposed action                    |
| --- | -------------------------- | --------------------- | ---------- | ---------- | ------------------------------ | ---------------------------------- |
| C-1 | Use npm for all commands.  | `DELETE`              | stale      | high       | `package.json` uses pnpm.      | Remove after backup and approval.  |
| C-2 | API handlers use format X. | `MOVE TO CLAUDE RULE` | useful     | medium     | Applies only under `src/api/`. | Move to path-scoped rule.          |
| C-3 | Never deploy production.   | `MOVE TO HOOK`        | unenforced | high       | Context text cannot enforce.   | Recommend a PreToolUse hook guard. |

## Settings And Hook Recommendations

- Settings: consider `claudeMdExcludes` for irrelevant parent repo instructions.
- Hooks: add a PreToolUse hook only after explicit approval.
- Managed policy: no managed-policy change proposed.

## Recommended Next Action

Invoke a cleanup route explicitly if C-1 and C-2 should be applied; `plan-run-cleanup-file` is Recommended.
rea-analysis-optimizationmorluto/reaOptimize REA providers and shared analysis workflows for agent context, latency, CPU, and memory while preserving correctness and Evidence. Use for analysis bottlenecks and cache or query design; CI/test-suite optimization belongs to rea-ci-tests-audit.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
rea-ci-tests-auditmorluto/reaAudit REA CI and test suites for correctness, fixture drift, false passes, and measured performance; use for suite or workflow investigations and efficiency changes, rather than ordinary feature testing or a single test failure.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
rea-tool-designmorluto/reaAudit, investigate, design, or change REA investigation tools, CLI/MCP contracts, provider capabilities, and Evidence semantics.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
ponytail-auditDietrichGebert/ponytailQuality audit of the whole repo: bugs, security, real load, missing tests, speed, and what to delete. Most important first.Stars: 194kUpdated Claude CodeCodexVerifiedInstall