skills/olakai-status/SKILL.md
Show your Olakai developer Coding IQ status — monitoring health, personal spend, and budget. AUTO-INVOKE when user asks about: their Olakai monitoring health, personal AI spend, budget status, Coding IQ digest, whether their workspace is monitored, how much they've spent on AI this month, whether they're approaching their budget limit, or wants a quick overview of their Olakai coding status. TRIGGER KEYWORDS: olakai status, my spend, my budget, coding iq status, am I monitored, monitoring health, personal spend, budget limit, how much have I spent, olakai digest, coding status, my olakai, workspace monitored, check my olakai. DO NOT load for: setting up monitoring (use olakai-monitor-local-coding-agent), troubleshooting events or KPIs (use olakai-troubleshoot), generating analytics reports (use olakai-reports), or creating new agents (use olakai-new-project).
npx skillsauth add olakai-ai/olakai-skills olakaiInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
This skill fetches your Olakai Coding IQ status and formats it as a clean in-terminal digest — monitoring health, personal spend, and budget — without leaving Claude Code.
which olakai || echo "NOT_INSTALLED"
If the output is NOT_INSTALLED, tell the user:
The Olakai CLI is not installed. Run
npm install -g olakai-clithen try again.
Stop here if not installed.
olakai status --json 2>&1
Parse the output as JSON. The shape is:
{
"localMonitor": {
"workspaces": [
{ "tool": "claude-code", "agentId": "...", "workspacePath": "...", "configured": true }
]
},
"backend": {
"identity": { "found": true, "displayName": "[email protected]", "identityCount": 2, "projectNames": ["Backend Services"] },
"spend": { "mtdCents": 1208, "providers": [...], "forecastMonthEndCents": 4030, "forecastConfidence": "high" },
"budget": { "found": true, "monthlyLimitCents": 5000, "alertThresholds": [80, 100], "usagePct": 24.2, "status": "ok", "forecastPct": 80.6 },
"monitoring": { "agentCount": 2, "recentSessionCount": 14, "lastActivityAt": "2026-06-09T12:00:00Z" }
},
"backendError": null
}
backendError is one of: null, "not logged in", "session expired", "unreachable", or another error string.
Use today's month and year in the heading (e.g., ## Olakai Status — June 2026).
Helper — formatting cents: divide by 100, show two decimal places. Examples:
1208 cents → $12.085000 cents → $50.000 cents → $0.00Helper — formatting a timestamp as relative time:
### Monitoring
- <tool display name>: ✓ configured (`<workspacePath>`)
- Last activity: <relative time> — <recentSessionCount> sessions this month
localMonitor.workspaces.localMonitor.workspaces is empty, show:
### Monitoring
- This workspace is not monitored.
tool display names: claude-code → "Claude Code", codex → "Codex CLI", cursor → "Cursor"backend.monitoring is null (offline) or backend is null, omit the "Last activity" line.backend.identity.found = true)### Personal Spend (<Month> MTD)
- Est. cost: **$<mtdCents formatted>**
- Forecast: ~$<forecastMonthEndCents formatted> by month-end *(<forecastConfidence> confidence)*
- Providers: <Provider 1> $<amount> · <Provider 2> $<amount>
forecastMonthEndCents is null.forecastConfidence label: "high" → "high", "medium" → "medium", "low" → "low", "insufficient_data" → omit the entire forecast line and note it in Action Items.backend.budget.found = true)### Budget
- Limit: $<monthlyLimitCents formatted>/month
- Used: <usagePct>% ($<mtdCents formatted> of $<monthlyLimitCents formatted>)
- Forecast: <forecastPct>% by month-end <status indicator>
Status indicators:
status = "ok" and forecastPct < 80 → no indicatorstatus = "ok" and forecastPct >= 80 → ⚠️ (approaching limit)status = "warning" → ⚠️ (approaching limit)status = "exceeded" → 🚨 (limit exceeded)Omit the Forecast line if forecastMonthEndCents is null.
backend.identity.found = true)### Identity
- Recognized as: <displayName> (<identityCount> identities)
- Projects: <projectNames joined by ", ">
Omit the Projects line if projectNames is empty.
Collect all applicable items and append an ### Action Items section at the end. Omit the section entirely if there are no items.
| Condition | Action Item |
|-----------|-------------|
| localMonitor.workspaces is empty | [ ] This workspace is not monitored. Run \olakai monitor init` to set it up.| |backendError = "not logged in"|[ ] Log in with `olakai login` to see your personal spend and budget.| |backendError = "session expired"|[ ] Your session has expired. Run `olakai login` to refresh.| |backendError = "unreachable"|[ ] Could not reach the Olakai backend. Local monitoring is still active. Check your network or try again later.| |backend.identity.found = false(and no backendError) |[ ] You are not yet recognized in Olakai Coding IQ. Your first session needs to be processed — this usually takes a few minutes after your first monitored session.| |backend.budget.status = "warning"|[ ] Your spend is approaching your budget limit ($<limit>). Forecast: <forecastPct>% by month-end. Contact your admin if you need a higher limit.| |backend.budget.status = "exceeded"|[ ] Your budget limit ($<limit>) has been exceeded. Contact your admin to request an increase.| |backend.spend.forecastConfidence = "insufficient_data"|[ ] Forecast not available yet — less than 5 days of spend data. Check back later.` |
## Olakai Status — June 2026
### Monitoring
- Claude Code: ✓ configured (`/Users/alice/dev/my-project`)
- Last activity: 2 hours ago — 14 sessions this month
### Personal Spend (June MTD)
- Est. cost: **$12.08**
- Forecast: ~$40.30 by month-end *(high confidence)*
- Providers: Anthropic $10.20 · Cursor $1.88
### Budget
- Limit: $50.00/month
- Used: 24.2% ($12.08 of $50.00)
- Forecast: 80.6% by month-end ⚠️ (approaching limit)
### Identity
- Recognized as: [email protected] (2 identities)
- Projects: Backend Services
### Action Items
- [ ] Your forecast (80.6%) is approaching your budget limit ($50.00). Contact your admin if you need a higher limit.
| Situation | What to show |
|-----------|--------------|
| backend = null or backendError present | Show Monitoring section, skip Spend/Budget/Identity, put the error in Action Items |
| budget.found = false | Skip Budget section entirely |
| identity.found = false | Skip Personal Spend and Identity sections; add Action Item |
| forecastMonthEndCents = null | Omit Forecast line from both Spend and Budget |
| localMonitor.workspaces is empty | Show "not monitored" message; add Action Item |
| CLI command fails (non-JSON output) | Show the raw error and suggest olakai login or olakai whoami |
tools
Set up and self-heal Olakai monitoring for the coding tool you are using — Claude Code, OpenAI Codex CLI, Cursor, Google Gemini CLI, or Antigravity CLI. Installs hooks, creates the agent record, and explains how to enrich events with KPIs. This is the skill for "monitor my coding tool itself" (not for instrumenting your own agent's source code with the SDK — that is olakai-integrate). AUTO-INVOKE when user wants to: monitor Claude Code / Codex / Cursor / Gemini CLI / Antigravity CLI sessions, monitor THIS coding tool, add observability to a local coding agent, track my own coding-assistant usage, set up olakai monitoring in this workspace, see what is being monitored on this machine, check if monitoring is working, or enable / repair hooks-based monitoring for any local coding agent. TRIGGER KEYWORDS: olakai monitor, monitor my coding tool, monitor this tool, monitor claude code, monitor codex, monitor cursor, monitor gemini cli, monitor antigravity, codex cli, cursor hooks, gemini cli, gemini-cli hooks, antigravity cli, antigravity, agy, local coding agent, local agent monitoring, olakai hooks, olakai monitor init, olakai monitor list, olakai monitor doctor, olakai monitor repair, monitor workspace, track sessions, is my monitoring working, monitoring not working, no events from claude code, claude code monitoring, codex monitoring, cursor monitoring, agents mine, where am i monitoring. DO NOT load for: instrumenting your own agent's SDK code (use olakai-integrate), creating agents from scratch with custom code (use olakai-new-project), generic SDK / KPI / event troubleshooting unrelated to a coding tool (use olakai-troubleshoot).
tools
Diagnose and repair Olakai monitoring for a local coding tool you already set up — Claude Code, OpenAI Codex CLI, or Cursor. Drives `olakai monitor list`, `olakai monitor doctor [--fix]`, and `olakai monitor repair` to self-heal hooks-based monitoring (no events, missing KPIs, broken/deleted agent, drifted config). For first-time setup use olakai-monitor-local-coding-agent instead. AUTO-INVOKE when user says: my coding-tool monitoring isn't working, no events from Claude Code / Codex / Cursor, is monitoring on / working, check my olakai monitoring, what's monitored on this machine, monitor doctor, monitor repair, monitor list, fix my monitoring, my monitored agent disappeared / 404, hooks stopped firing, re-link my monitoring key. TRIGGER KEYWORDS: olakai monitor doctor, olakai monitor repair, olakai monitor list, monitor not working, no events claude code, no events codex, no events cursor, fix monitoring, repair monitoring, agent 404, agent missing, hooks stopped firing, drift, registry, agents mine, where am i monitoring, is my monitoring working, self-heal monitoring. DO NOT load for: first-time setup of a coding tool (use olakai-monitor-local-coding-agent), instrumenting your own agent's SDK code (use olakai-integrate), generic SDK / KPI / event troubleshooting unrelated to a coding tool (use olakai-troubleshoot).
tools
Diagnose and fix issues with events, KPIs, custom data, or SDK integration. AUTO-INVOKE when user mentions: events not appearing, KPIs showing wrong values, KPIs showing strings instead of numbers, custom data missing, null KPIs, authentication errors, CLI not working, events not associated with agent, monitoring broken, SDK errors, or any Olakai-related problem. TRIGGER KEYWORDS: olakai, troubleshoot, debug, not working, events missing, KPI wrong, KPI null, KPI string, customData missing, authentication failed, CLI error, no events, events not appearing, diagnose, fix olakai, broken, SDK error, monitoring issue, API key invalid, events not tracked. DO NOT load for: initial setup (use olakai-new-project or olakai-integrate), or generating reports (use olakai-reports).
tools
Generate usage summaries, KPI trends, ROI reports, and compliance analytics from the terminal. AUTO-INVOKE when user wants: usage summaries, KPI trends, risk analysis, ROI reports, efficiency metrics, agent comparisons, token usage reports, cost analysis, compliance reports, or any analytics without using the web dashboard. TRIGGER KEYWORDS: olakai, analytics, reports, usage summary, KPI trends, risk analysis, ROI, efficiency, agent comparison, token usage, cost analysis, metrics report, dashboard data, CLI analytics, terminal report, compliance, usage report, event summary, performance metrics, AI usage stats. DO NOT load for: setting up monitoring (use olakai-integrate), troubleshooting (use olakai-troubleshoot), or creating new agents (use olakai-new-project).