Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/CES-Ltd/Luminpx agentmods add commands/ces-ltd/lumi/octo-sentinelWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/ces-ltd/lumi/octo-sentinel)<a href="https://agentmods.dev/commands/ces-ltd/lumi/octo-sentinel"><img src="https://agentmods.dev/badge/commands/ces-ltd/lumi/octo-sentinel/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/ces-ltd/lumi/octo-sentinel"><img src="https://agentmods.dev/badge/commands/ces-ltd/lumi/octo-sentinel.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00016 | $0.01465 |
| Opus 5 | $0.00008 | $0.00732 |
| Sonnet 5 | $0.00003 | $0.00293 |
| Haiku 4.5 | $0.00002 | $0.00146 |
Grade A, and why
octo-sentinel scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
**Implementation:** Canary uses the Bash tool with `curl` for HTTP checks, and optionally the browser MCP (Playwright or Chrome DevTools) for screenshot comparison and console monitoring if available. Falls back to `curl How it starts
The opening of the file, as written. The whole thing — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Sentinel (/octo:sentinel)
MANDATORY COMPLIANCE — DO NOT SKIP
When the user invokes /octo:sentinel, you MUST execute the structured triage workflow below. You are PROHIBITED from:
- Manually checking GitHub status without running the sentinel pipeline
- Skipping the triage scan and just reading
ghoutput directly - Deciding there's "nothing to triage" without actually running the checks
- Substituting a quick
gh pr listfor the full sentinel workflow
The user chose /octo:sentinel for structured, prioritized triage — not a raw gh dump.
Your first output line MUST be: 🐙 Octopus Sentinel
GitHub-aware work monitor that triages issues, PRs, and CI failures. Sentinel observes and recommends workflows but never auto-executes them.
Usage
/octo:sentinel # One-time triage scan
/octo:sentinel --watch # Continuous monitoring
/octo:sentinel --canary # Post-deploy canary monitoring
/octo:sentinel --canary URL # Monitor specific URL after deploy
What Sentinel Monitors
| Source | Filter | Recommended Action |
|---|---|---|
| Issues | octopus label |
Classified via task type → workflow recommendation |
| PRs | Review requested | /octo:ink for code review |
| CI Runs | Failed status | /octo:debug for investigation |
| Deployments | Post-deploy health | Canary alerts → /octo:debug |
Canary Mode (Post-Deploy Monitoring — Auto-Triggered)
Auto-trigger: Canary runs automatically when:
- The
/octo:deliverphase completes successfully (post-validation health check) - Sentinel
--watchmode detects a new deployment viagh api(deployment event) - The user runs
git pushto a branch with an active Vercel/Netlify/Railway deployment
No manual --canary flag needed — sentinel detects deployments and starts monitoring.
When invoked explicitly with --canary, or auto-triggered, sentinel switches to post-deploy health monitoring:
- Detect deployment — reads the latest Vercel/GitHub deployment or uses the URL argument
- Baseline capture — screenshots + console output + performance timing from pre-deploy (or first run)
- Health checks (runs every 60s for 5 minutes, then every 5 minutes):
- Page loads without errors (HTTP 200, no uncaught exceptions)
- Console error detection (new errors not in baseline)
- Core Web Vitals regression (LCP, CLS, FID compared to baseline)
- Key UI elements render (checks for empty/broken layouts)
- Alert on anomalies — if any check fails, sentinel reports:
🐙 Sentinel Canary Alert ⚠ [anomaly type]: [description] Baseline: [expected] | Current: [observed] Recommendation: /octo:debug "[anomaly description]" - Results — written to
.octo/sentinel/canary-<timestamp>.md
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 12d ago First seen · 142 lines · 16 tokens per session scan A c226d3c15d3b
octo-sentinel is a command published in the GitHub repository CES-Ltd/Lumi (31 stars, last pushed 4mo ago), licensed MIT. It adds 16 tokens to every session and 1,465 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other commands, from other repositories
performance-optimization
Orchestrate end-to-end application performance optimization from profiling to monitoring.
refactor-clean
You are a code refactoring expert specializing in clean code principles, SOLID design patterns, and modern software engineering best practices. Analyze and refactor the provided code to improve its quality, maintainability, and performance.
status
Display project status, active tracks, and next actions.
manage
Manage track lifecycle: archive, restore, delete, rename, and cleanup.
bootstrap
Verifies and repairs the Claude Code Toolkit installation.
update-counts
Update all hardcoded counts (skills, agents, marketplace repos/skills) across documentation from filesystem.