whiteboard: Skill for Claude Code

.claude/skills/workflow-authoring/SKILL.md

workflow-authoring is a skill for Claude Code from kamiazya/whiteboard. It costs 74 tokens per session (1,707 once invoked), scanned A, original, Apache-2.0.

Guidance for creating and maintaining Dynamic Workflows, which are scripts that coordinate coding-agent tasks. It covers workflows used for development loops, reviews, planning, investigation, and reconciliation.

In plain words
What is it for?
It is for editing or adding workflow scripts, debugging their inputs, combining workflows, and running parallel development loops.
Why use it?
It documents conventions and common mistakes, including how workflow inputs arrive and how workflows can call one another. This helps keep workflow scripts behaving as intended.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: reads .claude/ paths; mentions AGENTS.md; mentions Codex.

This is kamiazya/whiteboard's own configuration. It tells Claude Code how to work on whiteboard itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything whiteboard configures →

Part of the whiteboard plugin — 21 skills, 18 agents, 3 hooks shipped together

Reuse

Borrowing it

Nothing to install: this file belongs to kamiazya/whiteboard. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/kamiazya/whiteboard/main/.claude/skills/workflow-authoring/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/kamiazya/whiteboard

Made for: Claude Code.

Or install whiteboard, the plugin that ships this one along with the rest of its 21 skills, 18 agents, 3 hooks.

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 workflow-authoring

README.md
[![agentmods](https://agentmods.dev/badge/skills/kamiazya/whiteboard/workflow-authoring.svg)](https://agentmods.dev/skills/kamiazya/whiteboard/workflow-authoring)
Your own site
<a href="https://agentmods.dev/skills/kamiazya/whiteboard/workflow-authoring"><img src="https://agentmods.dev/badge/skills/kamiazya/whiteboard/workflow-authoring.svg" alt="Measured on agentmods" height="20"></a>
Per session 74 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,707 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00074 $0.01707
Opus 5 $0.00037 $0.00853
Sonnet 5 $0.00015 $0.00341
Haiku 4.5 $0.00007 $0.00171

Measured 8d ago against content hash 5800afd83a1c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

workflow-authoring 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.

.claude/skills/workflow-authoring/SKILL.md · 40 lines

How it starts

The opening of the file, as written. The whole thing — 40 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Workflow Authoring (whiteboard)

The repo's Dynamic Workflows live in .claude/workflows/*.workflow.mjs and are run via the Workflow tool. Roles: dev-loop (one task's inner loop) composes review (change-review gate, which has an optional inline dogfood phase); plan-initiative (multi-perspective planning) optionally composes consult-adversarial (Vet) and investigate (ground policy/hygiene/portability questions); dogfood-triage (standalone persona dogfooding); reconcile (pre-merge intent/conflict reconciliation); investigate (read-only, lightweight: fan out one investigator per concern dimension → synthesize a go/no-go with required-before-adopting steps; reusable for any "is it safe to commit/track X" question). The main session is the single integrator — it holds human gates (design approval, commit, PR, merge), git, and CI monitoring; workflows automate the rest and return needsHumanGate.

Gotchas (verified)

  1. args arrives as a JSON string, not an object. args.foo is always undefined → silent fallback to defaults. Normalize at the top of every script:

    const A = (() => { try { return typeof args === 'string' ? JSON.parse(args) : (args && typeof args === 'object' ? args : {}) } catch { return {} } })()
    

    Then read A.foo. (A no-arg args-probe workflow that return { typeofArgs: typeof args } confirms this.)

  2. Nesting is ONE level. workflow() inside a child throws. So dev-loop → review is fine, but review must NOT call workflow() — its dogfood is an inline phase (agent + Playwright), not a nested workflow. reconcile only detects/judges; the integrator does the actual fold.

  3. Parallel dev = main session fans out, not a parent workflow. A parent-workflow → dev-loop → review would be 2 levels. Instead the main session launches several dev-loop runs concurrently (each its own task), and folds results via reconcile.

  4. Parallel dev-loops run in isolated worktrees. A bare git worktree has no node_modules, but node .claude/scripts/new-worktree.mjs <name> [baseRef] does git worktree add .claude/worktrees/<name> + pnpm install --prefer-offline (~6s, warm pnpm store) so tests/typecheck run isolated there. Parallel pattern: the integrator (main session) creates one ready worktree per independent item, launches a dev-loop with cwd=<that worktree> (cwd-aware: git -C <cwd> + agents edit under it), runs several concurrently, then reconcile before folding. The main session stays at repo root (never cds away — see #5). A single-task dev-loop may still run on the main tree (implement stages only its files, never -A).

Read the full file on GitHub · 40 lines

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. 8d ago First seen · 40 lines · 74 tokens per session scan A 5800afd83a1c

Subscribe to this mod's changes

workflow-authoring is a skill published in the GitHub repository kamiazya/whiteboard (6 stars, last pushed today), licensed Apache-2.0. It adds 74 tokens to every session and 1,707 once invoked, about $0.0004 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

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

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…

microsoft/ai-agents-for-beginners · 200 tokens

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…

vercel/next.js · 95 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

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…

vercel/next.js · 103 tokens

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…

microsoft/vscode · 72 tokens