agentdeck-workflows

A set of step-by-step instructions for working on the AgentDeck project. AgentDeck includes a Stream Deck plugin, Android builds, and Apple or Xcode diagnostics.

In plain words
What is it for?
Building or running AgentDeck, packaging its Stream Deck plugin, creating Android releases, and investigating Apple or Xcode problems.
Why use it?
It gives the agent the project's required commands and rules for each kind of work instead of relying on guesses. It also identifies the project documents that must be checked first.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/puritysb/agentdeck/agentdeck-workflows
Any agent
npx skills add puritysb/AgentDeck --skill agentdeck-workflows
Clone the repo
git clone --depth 1 https://github.com/puritysb/AgentDeck

Made for: Claude Code, Codex.

Per session 44 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 332 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00044 $0.00332
Opus 5 $0.00022 $0.00166
Sonnet 5 $0.00009 $0.00066
Haiku 4.5 $0.00004 $0.00033

Measured 2d ago against content hash 252fd089997a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agentdeck-workflows 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 2d 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.

.agents/skills/agentdeck-workflows/SKILL.md · 30 lines

What it actually says

AgentDeck Workflows

Use this skill when the user asks to build, run dev mode, link/package the Stream Deck plugin, build Android, or debug an Apple/Xcode reproduction.

Required Context

  1. Read CLAUDE.md before running workflow commands.
  2. Read the top of DEVELOPMENT_LOG.md, then search it for the subsystem you are touching instead of loading the full file.
  3. Preserve App Store invariants from CLAUDE.md and AGENTS.md when touching Apple UI, daemon, setup, or diagnostics.

Workflow Map

  • Android release APK: read .agents/workflows/build-android.md.
  • Stream Deck plugin build/link: read .agents/workflows/build-plugin.md.
  • Dev watch mode: read .agents/workflows/start-dev.md.
  • Apple/Xcode diagnostics: read .agents/workflows/apple-xcode-debug.md.

Execution Rules

  • Treat the workflow file as the canonical command sequence for that task.
  • If a command requires network, GUI access, device access, or writes outside the workspace, request the scoped approval required by the current Codex sandbox.
  • For Apple/Xcode diagnostics, capture repository-side diagnostics before editing code when the issue was reproduced from Xcode.
  • Keep generated diagnostics under diagnostics/; do not commit them.
  • Report which workflow file was used and the verification result.
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. 2d ago First seen · 30 lines · 44 tokens per session scan A 252fd089997a

Subscribe to this mod's changes

agentdeck-workflows is a skill published in the GitHub repository puritysb/AgentDeck (212 stars, last pushed 2d ago), licensed MIT. It adds 44 tokens to every session and 332 once invoked, about $0.0002 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.