stark-ai-de/agent-skills / plugins/stark-ai-developer/skills/codex-memory-curator
codex-memory-curator
VerifiedAudit and safely curate Codex memory, including stale claims, cross-repo leakage, sensitive entries, and memory configuration. Use when reviewing or cleaning Codex memory, not generic repository docs.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 15.1 KB |
| agents/openai.yaml | config | 575 B |
| assets/cleanup-plan-template.md | markdown | 2.2 KB |
| assets/openai-icon.png | binary | 91.7 KB |
| assets/review-report-template.md | markdown | 2.3 KB |
| references/classification-rubric.md | markdown | 8.0 KB |
| references/config-modes.md | markdown | 15.9 KB |
| references/conflict-resolution.md | markdown | 1.6 KB |
| references/example-review-report.md | markdown | 4.0 KB |
| references/memory-store-anatomy.md | markdown | 2.2 KB |
| references/plan-lifecycle.md | markdown | 1.8 KB |
| references/review-procedure.md | markdown | 3.4 KB |
| references/safe-editing-procedure.md | markdown | 5.3 KB |
| scripts/backup-memories.mjs | script | 39.4 KB |
| scripts/inventory-memories.mjs | script | 4.6 KB |
| scripts/locate-memory-config.mjs | script | 2.7 KB |
| scripts/scan-memory-risks.mjs | script | 8.6 KB |
references/memory-store-anatomy.md
View on GitHub# Memory Store Anatomy
Use this when the memory directory contains multiple file types or generated evidence.
## Discovery Rule
Discover the local layout instead of assuming one fixed schema. Treat files under `<codex-home>/memories` as generated state unless a local instruction says otherwise.
Use `node scripts/inventory-memories.mjs --json` when file-kind grouping would make the review safer. The `kind` field is best-effort and should not override file contents or local instructions.
## Common Buckets
| Bucket | Examples | Default stance |
| ------------------------ | ---------------------------------------------------------- | ------------------------------------------------------------------------------------------- |
| Curated summaries | `memory_summary.md`, `MEMORY.md`, durable preference files | Review and propose focused rewrites or removals. |
| Recent/raw inputs | recent prompts, extracted memories, raw candidates | Inspect only as evidence; avoid hand edits unless sensitive data requires approved cleanup. |
| Supporting evidence | rollout/session summaries, JSONL traces, citations | Treat as append-only evidence; do not rewrite to fix a stale curated claim. |
| Skill or extension notes | skill-specific memories, ad hoc update notes | Follow the local note/update workflow; do not bypass it. |
| Backups | `memories.backup.*` | Do not scan as active memory unless the user asks to review backups. |
## Editing Guidance
- Prefer changing the smallest curated claim that affects future behavior.
- Do not rewrite generated evidence just because a summary is stale.
- If a generated evidence file contains sensitive data, propose removal or redaction only after backup and explicit approval.
- If schema ownership is unclear, defer the proposal in chat or the single curation record instead of editing the original or creating a sibling memory file.
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 |