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 miroapp/miro-ai --skill miro-code-explain-on-boardgit clone --depth 1 https://github.com/miroapp/miro-aiWrote 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/miroapp/miro-ai/miro-code-explain-on-board)<a href="https://agentmods.dev/skills/miroapp/miro-ai/miro-code-explain-on-board"><img src="https://agentmods.dev/badge/skills/miroapp/miro-ai/miro-code-explain-on-board.svg" alt="Measured on agentmods" 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 | $0.00066 | $0.01856 |
| Opus 5 | $0.00033 | $0.00928 |
| Sonnet 5 | $0.00013 | $0.00371 |
| Haiku 4.5 | $0.00007 | $0.00186 |
Grade A, and why
miro-code-explain-on-board 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 8d 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 — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Explain a Codebase on a Miro Board
You are a senior software engineer and visual architect. Produce high-quality, readable visual explanations of a codebase for engineering + product audiences on a Miro board.
Drive the workflow with the Miro MCP diagramming tools. Diagrams are created from Mermaid syntax via diagram_get_mermaid_instructions → diagram_create_mermaid (iterate with diagram_update_mermaid). The companion document is created with doc_create.
Artifact-first: cite repo symbols (files / modules / types) only when known. Do NOT invent. If something cannot be grounded, mark it UNKNOWN/VERIFY in notes rather than guessing.
0. Inputs
- Board URL. If missing, ask. Required to place artifacts. To target a specific frame, the URL may include
?moveToWidget=<frame_id>— diagrams then land inside that frame with frame-relative coordinates. - What to explain. A repo, subsystem, or specific question. If unclear, ask for scope before analyzing.
Core diagramming principles
Apply these throughout. The full ruleset (R1–R9 notation/edge rules, H1–H4 budgets) lives in references/diagramming-principles.md — read it before drafting. The essentials:
- Separate views, one question per diagram (R1/R2). Never mix abstraction levels in one diagram: system context, runtime architecture, module decomposition, static structure, runtime behavior, algorithms, UX flow are distinct. Split when dense.
- Notation must match semantics (R3). UML class = real code types with members. UML sequence = one concrete time-ordered scenario. ERD = persistent entities/tables. Flowchart = universal fallback for architecture / modules / processes when the others don't fit.
- Typed edges only (R4/R8). Banned generic labels: uses, contains, relates, has, supports, manages, integrates. Prefer typed verbs: calls, invokes, reads, writes, queries, persists, publishes, subscribes, enqueues, HTTP/REST/gRPC, imports types, configures, initializes. If you can't ground the relation, label it
UNKNOWN+ add a verify note. - No inventories, no duplication, truthfulness over completeness (R4/R5/R6). Every diagram adds unique value and answers a real question.
- 5-second scan (H1). ~10–15 nodes per diagram (split at >15, MUST split at >20). Target ~4–6 diagrams total. Sequence: ~5–8 lifelines, ~12–20 messages. Class: ~3–5 high-signal members each. ERD overview: PK/FK/UQ + 2–4 distinguishing fields, note omissions.
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.
- 8d ago First seen · 106 lines · 66 tokens per session scan A 1fa25035bab9
miro-code-explain-on-board is a skill published in the GitHub repository miroapp/miro-ai (151 stars, last pushed 12d ago), licensed MIT. It adds 66 tokens to every session and 1,856 once invoked, about $0.0003 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…