apd-miro

apd-miro is a skill for Claude Code, Codex from zstevovich/claude-apd. It costs 92 tokens per session (1,629 once invoked), scanned A, original, MIT.

A skill that updates a Miro board, an online visual workspace, with the current state of an APD development pipeline.

In plain words
What is it for?
Use it when a project has a configured Miro board and you need to show pipeline status, recent results, or task metrics.
Why use it?
It gives the team a shared visual view of active work, completed tasks, timings, and pipeline measurements.

Skill for Claude CodeCodex

Written for Claude Code and Codex: shipped in a Claude Code plugin, but also agents/openai.yaml present. Also seen: mentions AGENTS.md; mentions Codex.

Part of the claude-apd plugin — 11 skills, 5 agents, 8 hooks, 1 MCP server shipped together

Good fit Use it when a project has a configured Miro board and you need to show pipeline status, recent results, or task metrics.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/zstevovich/claude-apd/apd-miro
Install

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.

Any agent
npx skills add zstevovich/claude-apd --skill apd-miro
Clone the repo
git clone --depth 1 https://github.com/zstevovich/claude-apd

Made for: Claude Code, Codex.

Or install claude-apd, the plugin that ships this one along with the rest of its 11 skills, 5 agents, 8 hooks, 1 MCP server.

Wrote 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.

agentmods badge for apd-miro

README.md
[![agentmods](https://agentmods.dev/badge/skills/zstevovich/claude-apd/apd-miro/github.svg)](https://agentmods.dev/skills/zstevovich/claude-apd/apd-miro)
Your own site
<a href="https://agentmods.dev/skills/zstevovich/claude-apd/apd-miro"><img src="https://agentmods.dev/badge/skills/zstevovich/claude-apd/apd-miro/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.

agentmods 80×15 button for apd-miro

Your own site · 80×15
<a href="https://agentmods.dev/skills/zstevovich/claude-apd/apd-miro"><img src="https://agentmods.dev/badge/skills/zstevovich/claude-apd/apd-miro.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 92 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,629 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00092 $0.01629
Opus 5 $0.00046 $0.00814
Sonnet 5 $0.00018 $0.00326
Haiku 4.5 $0.00009 $0.00163

Measured 10d ago against content hash 6d93a886fc7e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

apd-miro 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 10d 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.

plugins/apd/skills/apd-miro/SKILL.md · 179 lines

How it starts

The opening of the file, as written. The whole thing — 179 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Miro Pipeline Dashboard (Codex)

Creates or updates a pipeline dashboard on the Miro board with:

  • Current pipeline status (which step is active)
  • Recently completed tasks with durations
  • Pipeline metrics (averages, skip rate)

When to use / When to skip

Use when:

  • The project has MIRO_BOARD_URL configured in AGENTS.md
  • A pipeline cycle just completed — update the board with the new result
  • The user asked: "update Miro dashboard"
  • Start of a session — display current pipeline state on the board

Skip when:

  • No Miro board is configured for the project (no MIRO_BOARD_URL)
  • The Miro MCP server is not connected or authenticated
  • The pipeline hasn't moved since the last update — the board would show the same state

Prerequisite

  • Miro MCP server registered in .codex/config.toml (HTTP transport: https://mcp.miro.com)
  • MCP authentication completed (Codex prompts on first call)
  • MIRO_BOARD_URL defined in AGENTS.md

Procedure

1. Gather data

Pull pipeline state and historical metrics through MCP tools:

apd:apd_pipeline_state()                    # current step + step timings
apd:apd_pipeline_metrics()                  # historical runs (timestamp, phase ts, status, adversarial T/A/D, agent counts)

Compute averages and skip rate from the runs list returned by apd:apd_pipeline_metrics(). Pass limit=N to cap the most recent N runs (0 = all, max 200).

2. Create dashboard table on the board

Use Miro MCP create_table to create the dashboard:

Table 1: Pipeline Status

Step Status Time
Spec ✅ / ⏳ / — timestamp
Builder ✅ / ⏳ / — timestamp
Reviewer ✅ / ⏳ / — timestamp
Verifier ✅ / ⏳ / — timestamp
  • ✅ = completed (green sticky note)
  • ⏳ = in progress (yellow sticky note)
  • — = not started (gray sticky note)

3. Create metrics section

Use Miro MCP create_document for a markdown document:

# APD Pipeline Metrics

**Total tasks:** {count}
**Average duration:** {time}
**Fastest task:** {time}
**Slowest task:** {time}
**Skip rate:** {percentage}

## Average per step
- spec→builder: {time}
- builder→reviewer: {time}
- reviewer→verifier: {time}

Read the full file on GitHub · 179 lines

Files

What ships with it

4 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.

Changes

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.

  1. 10d ago First seen · 179 lines · 92 tokens per session scan A 6d93a886fc7e

Subscribe to this mod's changes

apd-miro is a skill published in the GitHub repository zstevovich/claude-apd (5 stars, last pushed 1mo ago), licensed MIT. It adds 92 tokens to every session and 1,629 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 2026-08-31.

Related

Other skills, from other repositories