instinct-status — Claude Code command: status and setup
Review learned instincts with their confidence levels, domains, and sources. Use the command to inspect what the agent has picked up from its observations.
MIT ★ 880 updated 2026-09-03
.claude/commands/instinct-status.mdWhat instinct-status does
Run /instinct-status to call a Python script that reads personal and inherited instincts under ~/.claude/homunculus/instincts/ and groups them by domain. Each entry shows its action, trigger, confidence, and source. The command invokes ~/.claude/skills/continuous-learning-v2/scripts/instinct-cli.py, so Python 3 is required.
Filters narrow the results by domain, source, or confidence; --json formats the output for programmatic use. For example, --low-confidence shows entries below 0.5 confidence. The command cannot display a status if the script is missing from the path it calls.
What it helps with
- review instincts learned by the agent
- filter instincts by domain or source
- find entries with low confidence
- export the instinct list as JSON
Example prompts for the agent
- Show the learned instincts with
/instinct-status. - Filter the list to
code-styleusing/instinct-status --domain code-style. - Show low-confidence entries with
/instinct-status --low-confidence.
How to install instinct-status
Manually: put the files in place
.claude/commands/instinct-status.mdCall it with /instinct-status. For all projects use ~/.claude/commands/
Manually: put the files in place
~/.codex/prompts/instinct-status.mdCall it with /prompts:instinct-status. Codex marks this format deprecated in favour of skills
Manually: put the files in place
.github/prompts/instinct-status.prompt.mdManually: put the files in place
.gemini/commands/instinct-status.tomlGemini stores commands as TOML: the prompt text goes into the prompt field
Questions about instinct-status
How do I install instinct-status in Claude Code?
Add the command file at .claude/commands/instinct-status.md. Then invoke it with /instinct-status.
What does instinct-status do?
It reads personal and inherited instincts, groups them by domain, and displays each entry's confidence, trigger, and source.
Which filters does instinct-status support?
Use --domain <name> or --source <type> to filter entries, and --low-confidence or --high-confidence to filter by confidence. The --json flag returns JSON output.
Source text
instinct-status.md · MIT
--- name: instinct-status description: Show all learned instincts with their confidence levels command: /instinct-status implementation: python3 ~/.claude/skills/continuous-learning-v2/scripts/instinct-cli.py status --- # Instinct Status Command Shows all learned instincts with their confidence scores, grouped by domain. ## Implementation ```bash python3 ~/.claude/skills/continuous-learning-v2/scripts/instinct-cli.py status ``` ## Usage ``` /instinct-status /instinct-status --domain code-style /instinct-status --low-confidence ``` ## What to Do 1. Read all instinct files from `~/.claude/homunculus/instincts/personal/` 2. Read inherited instincts from `~/.claude/homunculus/instincts/inherited/` 3. Display them grouped by domain with confidence bars ## Output Format ``` 📊 Instinct Status ================== ## Code Style (4 instincts) ### prefer-functional-style Trigger: when writing new functions Action: Use functional patterns over classes Confidence: ████████░░ 80% Source: session-observation | Last updated: 2025-01-22 ### use-path-aliases Trigger: when importing modules Action: Use @/ path aliases instead of relative imports Confidence: ██████░░░░ 60% Source: repo-analysis (github.com/acme/webapp) ## Testing (2 instincts) ### test-first-workflow Trigger: when adding new functionality Action: Write test first, then implementation Confidence: █████████░ 90% Source: session-observation ## Workflow (3 instincts) ### grep-before-edit Trigger: when modifying code Action: Search with Grep, confirm with Read, then Edit Confidence: ███████░░░ 70% Source: session-observation --- Total: 9 instincts (4 personal, 5 inherited) Observer: Running (last analysis: 5 min ago) ``` ## Flags - `--domain <name>`: Filter by domain (code-style, testing, git, etc.) - `--low-confidence`: Show only instincts with confidence < 0.5 - `--high-confidence`: Show only instincts with confidence >= 0.7 - `--source <type>`: Filter by source (session-observation, repo-analysis, inherited) - `--json`: Output as JSON for programmatic use
© sangrokjung · MIT · sangrokjung/claude-forge