stark-ai-de/agent-skills / skills/claude-operations/claude-memory-curator
claude-memory-curator
VerifiedAudit 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.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 13.8 KB |
| assets/cleanup-plan-template.md | markdown | 2.0 KB |
| assets/review-report-template.md | markdown | 2.3 KB |
| references/classification-rubric.md | markdown | 5.6 KB |
| references/conflict-resolution.md | markdown | 1.9 KB |
| references/context-surface-anatomy.md | markdown | 4.2 KB |
| references/example-review-report.md | markdown | 2.3 KB |
| references/plan-lifecycle.md | markdown | 1.8 KB |
| references/review-procedure.md | markdown | 2.8 KB |
| references/safe-editing-procedure.md | markdown | 5.5 KB |
| references/settings-and-hooks.md | markdown | 1.6 KB |
| scripts/backup-claude-memory.mjs | script | 42.1 KB |
| scripts/inventory-claude-memory.mjs | script | 12.6 KB |
| scripts/memory-source-discovery.mjs | script | 2.2 KB |
| scripts/scan-claude-memory-risks.mjs | script | 11.5 KB |
assets/cleanup-plan-template.md
View on GitHub# Claude Context Cleanup Plan
Embed this structure in the `Plan` section of the selected route's chat result or single file record. Do not persist it as a second curation artifact.
## Scope
- Repo:
- Claude home:
- Auto memory directory:
- Requested by:
- Created:
- Plan approval status and evidence: record current or earlier approval of this unchanged plan
- Host Plan state / actual write permission:
- Material drift since approval:
- Backup required before edits: yes
## Entries
| ID | Source | Line | Current claim | Classification | Risk tags | Confidence | Conflict source | Proposed action | Proposed replacement | Approved |
| --- | ------ | ---- | ------------- | -------------- | --------- | ---------- | --------------- | --------------- | -------------------- | -------- |
## Manual Actions
| ID | Surface | Recommendation | Reason |
| --- | ------- | -------------- | ------ |
## Backup Contract
- Mode: `exact`
- Storage policy: `outside-git-worktree`; default to the deterministic per-repository user-state root
- Explicit storage override: `--backup-root PATH --backup-root-alias NAME` only when PATH is outside every Git worktree and NAME is a stable non-sensitive alias
- Repository receipt locator: script-reported portable storage locator plus manifest-relative paths only; absolute paths stay in non-persisted chat
- Exact include paths: one entry for every file that may change
- Required manifest: `backup-manifest.json`
- Receipt rule: Every pre-existing changed file must match exactly one verified manifest source entry; an approved new file is `created-no-preimage` with an explicit rollback
## Edit Rules
- Apply only rows with `Approved` set to `yes` in a plan-run route; direct cleanup uses a separately identified high-confidence atomic set.
- Back up only the exact Claude memory and instruction files that may change before edits.
- Do not edit managed policy files unless the user explicitly asks and the environment supports it.
- Redact sensitive values in reports and diffs.
- Re-read changed sections after edits.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| 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: 472k | Updated | Claude CodeCodex | Verified | Install |
| 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: 472k | Updated | Claude CodeCodex | Verified | Install |
| rea-tool-designmorluto/reaAudit, investigate, design, or change REA investigation tools, CLI/MCP contracts, provider capabilities, and Evidence semantics. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-auditDietrichGebert/ponytailQuality audit of the whole repo: bugs, security, real load, missing tests, speed, and what to delete. Most important first. | Stars: 194k | Updated | Claude CodeCodex | Verified | Install |