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/robofinsystems/robosystems/deploygit clone --depth 1 https://github.com/RoboFinSystems/robosystemsWhat 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 | $0.00018 | $0.01347 |
| Opus 5 | $0.00009 | $0.00674 |
| Sonnet 5 | $0.00004 | $0.00269 |
| Haiku 4.5 | $0.00002 | $0.00135 |
Grade A, and why
deploy 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 2d 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.
curl -sf https://<api-host>/v1/status && echo OK # public API over HTTPS How it starts
The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Monitor a deployment run — pinpoint why it failed, drive it to green on a re-run, and verify health. Deploys go through GitHub Actions (workflow_dispatch); this skill is about watching and diagnosing them, not replacing the pipeline. Pairs with the deployment-monitoring runbook in local/RoboSystems/runbooks/ for account-specific stack names and failure classes — read it alongside this file.
When this runs
Most deploys (~95%) go green untouched and need no attention. The real use case is the other 5%: a deploy failed, and you're re-running it and want eyes on this one. Optimize for that — get to the failing job fast, classify it, fix the cause, re-trigger, and confirm the app is healthy afterward.
Scope & guardrails
ghreads are free; the deploy trigger is not. Reading runs, jobs, and logs (gh run list/view/watch) needs no confirmation. Triggering or re-triggering a deploy (gh workflow run,just deploy) is an outward-facing action — confirm the target (env + ref) with the user first, and default to watching a run they already started.- AWS is read-only here.
describe-*/list-*only. CloudFormation changes and stack deletions are the user's to run — nevercreate-stack/update-stack/delete-stackdirectly. - Never deploy the default branch to prod. Production should ride a version tag / release branch produced by the release workflow. Verify the ref before triggering rather than assuming the pipeline will reject a bad one, and when reviewing history (
gh run list --json headBranch,displayTitle), flag any past prod run that rode a branch rather than a tag. just deploydefaults are dangerous if you're not explicit. The recipe defaults to the prod environment and the current branch. Always pass both arguments.- Output can be sensitive. Failure logs name internal hostnames, stack names, and resource IDs. Don't paste raw infra detail into anything public; summarize.
1. Find the run
Identify env (staging | prod) and which run you're looking at. If the user didn't say, ask or infer from context.
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.
- 2d ago First seen · 73 lines · 18 tokens per session scan A 366a141d527d
deploy is a command published in the GitHub repository RoboFinSystems/robosystems (24 stars, last pushed 3d ago), licensed Apache-2.0. It adds 18 tokens to every session and 1,347 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
fill-event-triage
체결(fill) 이벤트, 특히 매도 체결 후 현금 재배치 판단을 read-only 트리아지로 자동 기동해 dry-run 제안을 남긴다. ROB-755.
crypto-alert-triage
Command "crypto-alert-triage" from mgh3326/auto_trader, covering crypto-alert-triage, 입력, 1. 맥락 복원 (반드시 이 순서), 2. 분석 and 3. dryrun 미리보기 (read-only).
akb-production-review
Review AKB production-governance docs and hooks.
feature
Post a feature to the Features Board on production and write tweets.
os-meeting
快速创建和管理AI团队会议.
cf-scaffold-project
Scaffold a Cloudflare project — Worker, Pages, or Worker+D1+R2 starter — with Wrangler config, Terraform skeleton, and GitHub Actions deploy using scoped API tokens.