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 olgasafonova/miro-mcp-server --skill miro-workflowgit clone --depth 1 https://github.com/olgasafonova/miro-mcp-serverWrote 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/olgasafonova/miro-mcp-server/miro-workflow)<a href="https://agentmods.dev/skills/olgasafonova/miro-mcp-server/miro-workflow"><img src="https://agentmods.dev/badge/skills/olgasafonova/miro-mcp-server/miro-workflow/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/olgasafonova/miro-mcp-server/miro-workflow"><img src="https://agentmods.dev/badge/skills/olgasafonova/miro-mcp-server/miro-workflow.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00103 | $0.03250 |
| Opus 5.5 | $0.00041 | $0.01300 |
| Sonnet 5.5 | $0.00021 | $0.00650 |
| Haiku 4.5 | $0.00010 | $0.00325 |
Grade A, and why
miro-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 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 — 256 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Miro Workflow Skill
Compose Miro boards from natural-language requests using the miro-mcp-server tools. The MCP exposes 91 atomic tools; this skill is the map.
Scope
If the request is a single-tool call ("create one sticky note"), a question about Miro the product, or read-only inspection ("what's on this board?"), exit and let Claude handle it directly. The skill's job is composition, not single-call wrapping. Routing happens via the description field, not this section.
The 5 workflows
Each workflow is a documented composition with default spatial values. Pick one based on intent:
| Workflow | Trigger Phrases | Detail File |
|---|---|---|
| Sprint Board | "sprint planning", "sprint board", "sprint kickoff" | workflows/sprint_board.md |
| Retrospective | "retro", "retrospective", "what went well" | workflows/retrospective.md |
| Brainstorm | "brainstorm", "ideation", "ideas around" | workflows/brainstorm.md |
| Story Map | "user story map", "story mapping", "user journey" | workflows/story_map.md |
| Kanban | "kanban", "task board", "workflow board" | workflows/kanban.md |
If the request doesn't match any of these, fall back to direct tool calls and ask the user what layout they want.
Optional: seed boards
Before falling back to from-scratch construction, check if the user has imported a Miroverse template into their account that matches the requested workflow. See seed-boards.md for the lookup pattern. Seed boards are an optional power-user path; they produce more polished output but require one-time setup. The from-scratch workflows below work without any setup.
Workflow selection guide
Goal: track sprint work? → sprint_board (4 columns: Backlog, In Progress, Review, Done)
Goal: reflect on the team? → retrospective (3 frames: Went Well, Could Improve, Action Items)
Goal: generate ideas? → brainstorm (radial: central topic, 6 stickies in a ring)
Goal: map a product? → story_map (header row + tasks + release swimlanes)
Goal: ongoing task flow? → kanban (configurable column count)
What ships with it
8 files 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 · 256 lines · 103 tokens per session scan A 72ee8ffa069b
miro-workflow is a skill published in the GitHub repository olgasafonova/miro-mcp-server (31 stars, last pushed yesterday), licensed MIT. It adds 103 tokens to every session and 3,250 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 2026-08-30.
Other skills, from other repositories
productplan-pm
Generates comprehensive workflows for product managers to manage roadmaps, OKRs, ideas, and launches in ProductPlan. Use when doing day-to-day product management work, updating feature timelines, tracking objectives, or triaging customer feedback.
productplan-workflows
Generates step-by-step workflows for managing ProductPlan roadmaps, OKRs, ideas, and launches via MCP server tools. Use when working with ProductPlan data, planning features, tracking objectives, or coordinating product launches.
productplan-customer-facing
Generates customer-ready roadmap views and launch timelines from ProductPlan for Sales and Customer Success teams. Use when preparing for customer calls, sharing product direction, or answering "when will feature X ship?" questions.
request-progress
Group recent conversations into overall requests, review each one's progress from memory, link each to the owner goals it serves, and write the build story, so My Work shows progress meters, shipping velocity and learned working preferences. Use when asked to "group requests", "group by overall request", "review…
slack
Read and search messages, channels, and threads in the user's Slack workspace. Use to catch up on team discussions and decisions, post channel messages, and reply to coworkers through Slack's official MCP server.
onboard
Onboarding doc for a new contributor or agent — project state, conventions, priorities relevant to the specified role.