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 agentmods add commands/ngocsangyem/meowkit/canarygit clone --depth 1 https://github.com/ngocsangyem/MeowKitWrote 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/ngocsangyem/meowkit/canary)<a href="https://agentmods.dev/commands/ngocsangyem/meowkit/canary"><img src="https://agentmods.dev/badge/commands/ngocsangyem/meowkit/canary.svg" alt="Measured on agentmods" 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 | $0.00358 |
| Opus 5 | $0.00000 | $0.00179 |
| Sonnet 5 | $0.00000 | $0.00072 |
| Haiku 4.5 | $0.00000 | $0.00036 |
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 6d 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 — Staged Deployment
Usage
/canary [deploy target]
Behavior
Staged deployment with monitoring and human-gated promotion. Uses mk:ship with canary deployment patterns.
Execution Steps
-
Assess if canary is warranted. Auto-detect based on changed files:
- Database migrations present → canary warranted
- Auth/security changes → canary warranted
- API contract changes → canary warranted
- Infrastructure/config changes → canary warranted
- UI-only changes with no backend impact → canary optional
- If canary is not warranted, inform the user and offer to proceed with standard deploy.
-
Deploy to canary environment.
- Deploy the current build to the canary/staging environment only.
- Canary receives a percentage of traffic (project-specific configuration).
- Print: deployment target, version/commit deployed, traffic percentage.
-
Print monitoring checklist. Provide a checklist for the human to verify:
🐱 Canary Monitoring Checklist: [ ] Error rate: no increase from baseline [ ] Latency p50/p95/p99: within acceptable range [ ] Key business metrics: no degradation [ ] Logs: no new error patterns [ ] Duration: observed for minimum [X] minutes -
Wait for human confirmation. Two options:
- Promote: roll out to 100% of traffic / production.
- Rollback: revert canary to previous version, no production impact.
Output
- Canary deployment status
- Monitoring checklist
- Awaiting human decision: promote or rollback
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.
- 6d ago First seen · 47 lines · 0 tokens per session scan A 3b810d98d795
canary is a command published in the GitHub repository ngocsangyem/MeowKit (14 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 358 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 2026-08-30.
Other commands, from other repositories
valuation-methods
Valuation methods analysis — multiples, DCF inputs, PEG integration, valuation assumption extraction.
genshijin-compress
Markdown・テキストファイルを原始人形式へ安全圧縮.
enum-udp
UDP scan + service follow-up — top ports first, full sweep only when justified.
claude-recall
Update project context using the local LLM (Qwen2.5 0.5B).
review
Submit a story for verification (In Progress → In Review, no PR yet).
standup
Alias of /board — the async sprint snapshot.