Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add rijuvashisht/Magneto --skill canarygit clone --depth 1 https://github.com/rijuvashisht/MagnetoWrote 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/skills/rijuvashisht/magneto/canary)<a href="https://agentmods.dev/skills/rijuvashisht/magneto/canary"><img src="https://agentmods.dev/badge/skills/rijuvashisht/magneto/canary/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/skills/rijuvashisht/magneto/canary"><img src="https://agentmods.dev/badge/skills/rijuvashisht/magneto/canary.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 | $0.00000 | $0.00330 |
| Opus 5 | $0.00000 | $0.00165 |
| Sonnet 5 | $0.00000 | $0.00066 |
| Haiku 4.5 | $0.00000 | $0.00033 |
Grade A, and why
canary scanned grade A with 0 findings 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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
/canary — Post-Deploy Monitoring Loop
Role: SRE
Inputs: deployed URL
Outputs: continuous monitoring report; alerts on anomalies
Audit actions: canary.started, canary.anomaly_detected, canary.cleared
What This Skill Does
For the first 30–60 minutes after a deploy, actively monitor for:
- Console errors (new types not seen pre-deploy)
- Performance regressions (p95 page load > baseline × 1.5)
- Network errors (new 4xx/5xx rates)
- Feature flag misfires
Protocol
Step 1: Baseline
Run magneto browse against the previous deploy (or staging) to capture baseline metrics:
- Page load times
- Console message counts by level
- Network request counts
Step 2: Loop
Every 5 minutes for the configured window:
- Visit key pages via headless browser
- Capture metrics
- Diff vs baseline
- If anomaly exceeds threshold, emit audit
canary.anomaly_detectedand alert
Step 3: Alert channels
Configured via .magneto/canary.json:
- Slack webhook
- PagerDuty
- Terminal-only (default)
Step 4: Auto-rollback (opt-in)
If autoRollback: true and critical anomaly detected, run the rollback command and emit audit canary.rollback_triggered.
Trigger Phrases
- "canary"
- "monitor prod"
- "watch the deploy"
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 · 47 lines · 0 tokens per session scan A c3021620cb07
canary is a skill published in the GitHub repository rijuvashisht/Magneto (6 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 330 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
environments
How Open SWE environments work and how to change them — create one, edit or fork an existing one, start from scratch, what setupscript and updatescript are for, why a nightly refresh failed, where the build logs are, and how to read a rebuild in progress. Read this whenever someone asks about environments, snapshots…
langbot-deploy
Deploy and configure a LangBot instance — Docker / Docker Compose, Kubernetes, the config.yaml model, the Box sandbox runtime, the plugin runtime, and the global API key. Use when installing, deploying, upgrading, or configuring LangBot in production or self-hosted environments. Triggers on "deploy langbot", "langbot…
deploy-fullstack-vercel
Build and deploy a full-stack app (React frontend + Python/FastAPI backend) or a Vellum app to Vercel as a serverless demo with seeded data.
vercel-token-setup
Set up a Vercel API token for publishing apps using browser automation.
enterprise-agent-ops
Operate long-lived agent workloads with observability, security boundaries, and lifecycle management.
static-assets-hosting
Host static websites and assets via zip upload to Originless IPFS. Use when: (1) Deploying static sites, (2) Hosting HTML/CSS/JS projects, (3) Sharing web assets publicly, or (4) User asks to host static files.