status · wrg32786 — Claude Code skill: aigent-OS status and install
The status Claude Code skill reports the current operating state of aigent-OS. Ask for a snapshot of its mode, objective, next action, or blockers.
MIT ★ 26 updated 2026-11-16
npx skills add wrg32786/aigent-os --skill status -a claude-codeWhat status does
The skill refreshes aigent-OS runtime state and prints a compact terminal-style report. It includes the current mode and objective, the next valid action, context and memory pressure, the active capsule, blocked items, skill gaps, and active reflexes. The report stays under 12 lines.
It first runs python3 "$AIGENT_VAULT/daemons/runtime/update-active-state.py", then reads $AIGENT_VAULT/memory/runtime/ACTIVE_STATE.json. Python 3 and the AIGENT_VAULT environment variable are required; without that variable, the script path cannot be resolved. When a reflex is active, the report adds its action hint, such as a capsule recommendation or an escalation notice.
What it helps with
- check aigent-OS operating mode
- find the current objective and next valid action
- count blocked items and open skill gaps
- inspect context, memory, and token pressure
Example prompts for the agent
- Show the current aigent-OS runtime status.
- Check aigent-OS mode, objective, next action, and blocked items.
- List active reflexes and the current capsule in aigent-OS.
How to install status
1Skills CLI (Vercel)
npx skills add wrg32786/aigent-os --skill status -a claude-code2Manually: put the files in place
~/.claude/skills/status/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/status/
1Skills CLI (Vercel)
npx skills add wrg32786/aigent-os --skill status -a codex2Manually: put the files in place
.agents/skills/status/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add wrg32786/aigent-os --skill status -a cursor2Manually: put the files in place
.cursor/skills/status/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install wrg32786/aigent-os skills/status2Manually: put the files in place
.github/skills/status/SKILL.md1Skills CLI (Vercel)
npx skills add wrg32786/aigent-os --skill status -a gemini-cli2Platform CLI
gemini skills install https://github.com/wrg32786/aigent-os --path skills/statusManually: put the files in place
.devin/skills/status/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add wrg32786/aigent-os --skill status -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about status
How do I install status in Claude Code?
Run npx skills add wrg32786/aigent-os --skill status -a claude-code. The skill file is at ~/.claude/skills/status/SKILL.md.
What does status do?
It refreshes aigent-OS runtime state and prints a short report with the mode, objective, next action, pressure levels, blockers, and active reflexes.
What does status need to run?
It requires Python 3 and the AIGENT_VAULT environment variable pointing to the aigent-OS directory. The skill runs daemons/runtime/update-active-state.py and reads memory/runtime/ACTIVE_STATE.json.
Source text
SKILL.md · MIT
---
name: status
description: "Report aigent-OS operational status. Use when checking the current operational state of aigent-OS."
---
# /status — aigent-OS operational status
Read computed runtime state and display a concise operational summary. Under 12 lines.
## Trigger
`/status` — user-facing command. Also available to the AIgent internally.
## Flow
1. Run `python3 "$AIGENT_VAULT/daemons/runtime/update-active-state.py"` to refresh state
2. Read `$AIGENT_VAULT/memory/runtime/ACTIVE_STATE.json`
3. Format and display:
```
Mode: {mode}
Objective: {current_objective or "none"}
Next: {next_valid_action or "none"}
Pressure: context {p.context}, memory {p.memory}, token {p.token}
Capsule: {active_capsule.id or "none"} ({active_capsule.status})
Blocked: {count} items
Gaps: {count} open skill gaps
Reflexes: {list of true reflexes, or "none"}
```
4. If any reflexes are true, add a line: `Reflex: {reflex} — {action hint}`
- should_capsule → "Context pressure high — capsule recommended"
- should_digest → "Memory backlog >30 — /digest recommended"
- should_skill_hunt → "Open skill gaps — /skill-hunt queued"
- should_close → "Session >2hr — consider /close"
- should_escalate → "Blocked items — escalation needed"
## Output format
Keep it tight. Terminal-style. No prose. No headers. Just the state.
## Example
```
Mode: active
Objective: Build runtime state layer
Next: Wire /open and /close to read ACTIVE_STATE
Pressure: context low, memory medium, token low
Capsule: 2026-05-08-session38-close (active)
Blocked: 0 items
Gaps: 0 open
Reflexes: digest — Memory backlog >30
```
## Related
- `memory/runtime/ACTIVE_STATE.json` — the state this reads
- `memory/runtime/README.md` — schema docs
- `daemons/runtime/update-active-state.py` — the computer
- `/body-check` — deeper vital signs (somatic layer)
- `/open` and `/close` — compute state as part of session lifecycle
© wrg32786 · MIT · wrg32786/aigent-os
Similar skills
SKILL.md skills catalog →status by other authors comes first.