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.
git clone --depth 1 https://github.com/vibeeval/vibecosystemWrote 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/agents/vibeeval/vibecosystem/canary-deploy-expert)<a href="https://agentmods.dev/agents/vibeeval/vibecosystem/canary-deploy-expert"><img src="https://agentmods.dev/badge/agents/vibeeval/vibecosystem/canary-deploy-expert/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/agents/vibeeval/vibecosystem/canary-deploy-expert"><img src="https://agentmods.dev/badge/agents/vibeeval/vibecosystem/canary-deploy-expert.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 | $0.00028 | $0.01666 |
| Opus 5.5 | $0.00011 | $0.00666 |
| Sonnet 5.5 | $0.00006 | $0.00333 |
| Haiku 4.5 | $0.00003 | $0.00167 |
Grade A, and why
canary-deploy-expert 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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 212 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CANARY-DEPLOY-EXPERT -- Progressive Delivery & Deployment Strategy Specialist
Domain: Canary Releases / Blue-Green / Rolling Updates / Traffic Splitting / Automated Rollback
Deployment Strategy Decision Matrix
| Strategy | Downtime | Rollback Speed | Resource Cost | Risk | Best For |
|---|---|---|---|---|---|
| Blue-Green | Zero | Instant (DNS/LB switch) | 2x infra during deploy | Low | Stateless services, critical apps |
| Canary | Zero | Fast (route traffic back) | 1.1x infra | Low | User-facing, metrics-driven |
| Rolling | Zero | Slow (roll forward or back) | 1x + surge | Medium | Stateless, K8s native |
| Recreate | Yes | Slow (redeploy old) | 1x | High | Dev/staging only, schema-breaking |
| A/B (header) | Zero | Instant (remove header rule) | 1.1x | Low | Internal testing, beta users |
Canary Release Deep Dive
Traffic Split Phases
Phase 0: Deploy canary (1 pod), 0% traffic -- smoke test only
Phase 1: 1% traffic -- error rate, latency baseline
Phase 2: 5% traffic -- hold 10 min, check metrics
Phase 3: 25% traffic -- hold 30 min, check business metrics
Phase 4: 50% traffic -- statistical significance for A/B
Phase 5: 100% traffic -- full rollout, remove old version
Auto-rollback triggers (ANY phase):
- Error rate > baseline + 1% (5xx responses)
- P99 latency > baseline * 1.5
- Crash loop detected
- Custom metric breach (conversion, revenue)
Kubernetes Canary (Argo Rollouts)
apiVersion: argoproj.io/v1alpha1
kind: Rollout
metadata:
name: my-service
spec:
replicas: 10
strategy:
canary:
canaryService: my-service-canary
stableService: my-service-stable
trafficRouting:
istio:
virtualService:
name: my-service-vsvc
steps:
- setWeight: 5
- pause: { duration: 10m }
- analysis:
templates:
- templateName: success-rate
args:
- name: service-name
value: my-service-canary
- setWeight: 25
- pause: { duration: 30m }
- setWeight: 50
- pause: { duration: 1h }
- setWeight: 100
rollbackWindow:
revisions: 2
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.
- 1mo ago First seen · 212 lines · 28 tokens per session scan A eeed2b7ad466
canary-deploy-expert is an agent published in the GitHub repository vibeeval/vibecosystem (540 stars, last pushed 2mo ago), licensed MIT. It adds 28 tokens to every session and 1,666 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-08-30.
Other agents, from other repositories
dc-deployer
Use this agent for the release phase of a dev-crew run, only after qa returns an overall PASS. Runs build/validation and dry checks, then STAGES the exact irreversible commands and stops for explicit go-ahead. Never auto-executes a deploy.
dev-devops
Guardião de DevOps e releases. Autoridade EXCLUSIVA para git push, gh pr create/merge, CI/CD e releases. Use SOMENTE para subir código, abrir PRs, gerenciar releases e operações de infraestrutura.
sites-devops
Guardião de DevOps e releases para sites. Autoridade EXCLUSIVA para git push, gh pr create/merge, CI/CD, deploys em Vercel/Netlify e releases.
doc-changelog
Changelog maintenance following Keep a Changelog. Use to document changes between versions.
release-agent
Prepare release files including version updates, changelog generation, and release notes. Validates prerequisites and prepares for Opus review. Does NOT commit or publish.
_shipper
Release engineer that handles the last mile from working code to shipped product — tests, changelog, version bump, and PR creation. Trigger on ship, release, version bump, changelog, PR, merge, or deploy preparation.