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 skills/rome-os/rome/design-workflownpx skills add rome-os/rome --skill design-workflowgit clone --depth 1 https://github.com/rome-os/romeWrote 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/rome-os/rome/design-workflow)<a href="https://agentmods.dev/skills/rome-os/rome/design-workflow"><img src="https://agentmods.dev/badge/skills/rome-os/rome/design-workflow.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 | $0.00105 | $0.01337 |
| Opus 5 | $0.00053 | $0.00668 |
| Sonnet 5 | $0.00021 | $0.00267 |
| Haiku 4.5 | $0.00011 | $0.00134 |
Grade A, and why
design-workflow 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.
How it starts
The opening of the file, as written. The whole thing — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Design a workflow
The guardian described an automation. You take it from idea to an installed, runnable workflow app in this one conversation, in three phases: shape it into a spec → get approval → build it. There is no separate design surface, no intermediate plan format, and no hand-off — you do all three.
Phase 1 — Shape the idea into a spec
Turn what the guardian said into a short, plain-language spec they can read and sign off on. The spec is the thing they approve, so write it for a non-technical reader — what the automation does, not how it's coded. Use this shape:
Trigger — what kicks it off (a schedule, an event, a "run now"). Steps — the ordered things it does, one short verb phrase each ("fetch my unread emails", "summarize them", "post the digest to my chat"). Decisions — any branch ("if the total is over $5k, escalate; otherwise file it"), stated as plain conditions. Per-item work — anything done "for each" of a list ("for each ticket, rate its severity"). Delivers — the final step that sends, posts, saves, or shows the result.
Hold these disciplines while you shape it — they decide whether the spec is real:
- Ask the guardian for facts only they can supply; never invent them. A threshold amount, a recipient, a channel, which account, which event fires the trigger — a made-up "$5,000" looks authoritative and gets approved by accident. When a fact like this is missing, ask for it in your reply rather than guessing.
- Resolve design questions in conversation, not in the spec. Anything that changes the shape — whether to branch, what to do per item — gets settled with the guardian before you present the spec, not parked as an open question in it.
- Every workflow must deliver. A spec that only fetches and computes, with no step that sends/posts/saves/shows a result, has no destination and is never finished. If the guardian didn't say where the result goes, that's a fact to ask for (see above).
- Don't let vague quantifiers pass. "the top labs", "the latest news", "key themes", "top outlets" each hide a fact — how many, which sources, what time window. If it changes what the automation does, pin it down with the guardian.
- Keep it statically structured. The full space of what it does must be knowable before it runs: ordered steps, parallel work, a decision, or bounded per-item fan-out. No "keep polling until…", no unbounded loops.
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 · 92 lines · 105 tokens per session scan A 35ebbe0b072d
design-workflow is a skill published in the GitHub repository rome-os/rome (471 stars, last pushed today), licensed MIT. It adds 105 tokens to every session and 1,337 once invoked, about $0.0005 per session on Opus 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 skills, from other repositories
aos-router
Route one inbound user message to exactly one enabled AOS capability. This skill is a strategy contract only. Transport normalization, queueing, permissions, idempotency, audit events, retries, and capability execution stay in Rust.
code-studio-spec
Kiro-style Spec Mode for Code Studio: requirements, design, tasks, implementation, verification, and final report. Runtime sessions, candidate workspaces, diff approval, tests, and cancellation stay in Rust.
watchdog
Parse natural-language WatchDog questions into structured AgentOps queries. This skill documents the intent contract. Rust rules, permission checks, action guards, and fallback answers remain authoritative.
code-studio-code
Cursor/Codex-style coding workspace contract for ordinary Code Mode. This skill documents the behavior expected from the coding agent. Runtime sessions, workspace isolation, process execution, diff validation, and apply/reject actions stay in Rust.
nl2sql-reference
Strategy contract for user-bound reference files in Data Exploration. References can be README files, SQL demos, Python scripts, notebooks exported as text, metric dictionaries, or any UTF-8 text that explains business query patterns. Storage, upload validation, SQL safety, datasource permissions, and query execution…
pm-assistant
Product operations assistant strategy contract. PM short answers and deep analysis should be evidence-grounded and should separate facts from hypotheses. Model calls, hooks, queueing, cancellation, notifications, and staged task execution stay in Rust.