Files

OpenCode Test 55327c2e05 Add /remember, /config commands and memory helper scripts

New commands:
- /remember: Quick shortcut to save to memory (auto-categorizes)
- /config: View and manage configuration settings

New automation scripts:
- memory-add.py: Add items to PA memory with auto-categorization
- memory-list.py: List memory items by category

The /remember command provides a quick way to save:
- "Always use X" → preferences
- "Decided to use X" → decisions
- "Project at ~/path" → projects
- Other → facts

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

2026-01-01 12:23:39 -08:00

2.6 KiB

Raw Blame History

name, description, aliases

name

description

aliases

config

View and manage configuration settings

settings

prefs

/config Command

View and manage Claude Code configuration.

Subcommands

Subcommand	Description
(none)	Show current configuration summary
`show`	Show full configuration
`autonomy`	View/set autonomy level
`context`	View/set context level
`model`	View current model policy
`plugins`	List installed plugins

Usage

/config              # Summary view
/config show         # Full configuration
/config autonomy     # Current autonomy level
/config autonomy moderate  # Set autonomy level
/config context      # Current context level
/config context minimal    # Set for session
/config model        # Model policy
/config plugins      # Installed plugins

Implementation

Summary View (/config)

⚙️  Configuration Summary

Autonomy: conservative (default)
Context: moderate (default)
Model: opus (primary)

Plugins: 6 installed
Skills: 6 available
Commands: 16 available

Config files:
  ~/.claude/settings.json
  ~/.claude/state/autonomy-levels.json
  ~/.claude/state/model-policy.json

Autonomy (/config autonomy)

Read from: ~/.claude/state/sysadmin/session-autonomy.json

Levels:

conservative - Confirm all write operations
moderate - Auto-approve routine writes
trusted - Auto-approve most operations

# View
cat ~/.claude/state/sysadmin/session-autonomy.json

# Set (writes to session-autonomy.json)
echo '{"level": "moderate", "set_at": "timestamp"}' > session-autonomy.json

Context (/config context)

Read from: ~/.claude/state/personal-assistant/session-context.json

Levels:

none - Skip context gathering
minimal - Light context
moderate - Balanced (default)
comprehensive - Deep context scan

Model (/config model)

Read from: ~/.claude/state/model-policy.json

Shows:

Default models per agent
Escalation rules
Cost considerations

Plugins (/config plugins)

Read from: ~/.claude/plugins/installed_plugins.json

Installed Plugins:

• superpowers (4.0.2) - superpowers-marketplace
• frontend-design (6d3752c) - claude-plugins-official
• commit-commands (6d3752c) - claude-plugins-official
• typescript-lsp (1.0.0) - claude-plugins-official
• pyright-lsp (1.0.0) - claude-plugins-official
• superpowers-developing-for-claude-code (0.3.1) - superpowers-marketplace

Notes

Changes to autonomy/context are session-only unless using --set-default
Model policy changes require editing model-policy.json directly
Plugin management via /plugin command

2.6 KiB Raw Blame History