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 Koredotcom/agents-mcp-tools --skill arch-workflow-designgit clone --depth 1 https://github.com/Koredotcom/agents-mcp-toolsWrote 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/koredotcom/agents-mcp-tools/arch-workflow-design)<a href="https://agentmods.dev/skills/koredotcom/agents-mcp-tools/arch-workflow-design"><img src="https://agentmods.dev/badge/skills/koredotcom/agents-mcp-tools/arch-workflow-design/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/koredotcom/agents-mcp-tools/arch-workflow-design"><img src="https://agentmods.dev/badge/skills/koredotcom/agents-mcp-tools/arch-workflow-design.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 | $0.00089 | $0.01092 |
| Opus 5.5 | $0.00036 | $0.00437 |
| Sonnet 5.5 | $0.00018 | $0.00218 |
| Haiku 4.5 | $0.00009 | $0.00109 |
Grade A, and why
arch-workflow-design 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 — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Workflow design
A workflow is a durable, step-by-step run: each step runs once, retries are per step, and the run keeps its state while it waits. Agents call workflows through workflow tools. Most problems come from the call contract (sync vs async, timeout, inputs) or the version that actually runs.
Calling a workflow from an agent
| Setting | Rule |
|---|---|
| Mode | sync when the answer is needed this turn; async for long runs. Set mode (ABL) or toolMode (create_tool) explicitly: the agent file defaults to sync, while platform_workflows create_tool defaults to async |
| Timeout | Set timeout_ms (ABL) or timeoutMs (create_tool) to what the workflow really needs. Sync calls default to 60 s in the runtime (Studio offers 15 s); keep voice turns short and use async plus a status check for anything slow |
| Inputs | Declare typed, described inputs (the workflow's input schema or start node inputs) and a matching param_mapping. create_tool creates a tool with no arguments unless you pass parameters |
| Effect | Workflow tools are treated as side-effecting unless you declare effect: read_only |
| Unknown outcome | A sync call that cannot read the outcome fails with TOOL_WORKFLOW_OUTCOME_UNKNOWN. Never re-fire it; check the run with get_execution or the auto-wired check_workflow_status first |
| Async results | An async call returns an execution ID and running; the agent checks status with check_workflow_status |
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 75 lines · 89 tokens per session scan A 5d7c04890f21
arch-workflow-design is a skill published in the GitHub repository Koredotcom/agents-mcp-tools (4 stars, last pushed 1mo ago), licensed MIT. It adds 89 tokens to every session and 1,092 once invoked, about $0.0004 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 2026-10-09.
arch-workflow-design compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| arch-workflow-designKoredotcom/agents-mcp-tools | Skill | 4 | 1mo ago | MIT | A | 89 | Codex |
| mcp-tool-developersickn33/agentic-awesome-skills | Skill | 50k | today | MIT | A | 38 | Claude Code |
| mem0-oss-to-platformmem0ai/mem0 | Skill | 69k | 6d ago | Apache-2.0 | A | 217 | Claude Code, Codex |
| azure-mgmt-botservice-dotnetmicrosoft/skills | Skill | 3.2k | today | MIT | A | 78 | Claude Code |
| fastapi-router-pymicrosoft/skills | Skill | 3.2k | today | MIT | A | 46 | Claude Code |
| dev-runtimelangwatch/langwatch | Skill | 5.0k | today | Apache-2.0 | A | 172 | Claude Code |
| api-designericrisco/rsc-harness | Skill | 598 | today | MIT | A | 105 | Claude Code, Codex |