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/settings-and-hooks.md

View on GitHub
# Settings And Hooks

Use this when a Claude context entry should become enforceable configuration or automation.

## Settings Destinations

Prefer `MOVE TO SETTINGS` when the claim is about:

- enabling or disabling auto memory with `autoMemoryEnabled`;
- selecting a memory directory with `autoMemoryDirectory`;
- excluding irrelevant instruction files with `claudeMdExcludes`;
- permission allow or deny rules;
- sandbox filesystem or network restrictions;
- plugin, MCP, model, environment, or telemetry settings.

Use `.claude/settings.json` for shared project settings and `.claude/settings.local.json` for private local settings. Use `~/.claude/settings.json` for user-wide preferences. Treat managed settings as manual managed-policy actions unless explicitly in scope.

## Hook Destinations

Prefer `MOVE TO HOOK` when the claim requires lifecycle automation, validation, or a hard guard, such as:

- block a dangerous command before tool use;
- run a formatter or checker after edits;
- expand a prompt with generated context;
- reject or defer work when a policy condition fails;
- notify or log session events.

Use hook recommendations, not immediate hook edits, unless the user explicitly asks to create or modify hooks.

## Context Is Not Enforcement

`CLAUDE.md`, rules, and auto memory guide model behavior. They do not guarantee behavior. When the user says "must block", "never allow", or "enforce", classify the claim toward settings or hooks.

## Manual Managed Policy

Use `MOVE TO MANAGED POLICY` only for organization-wide requirements that should affect every Claude Code session on managed machines. Do not edit managed policy files by default.
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