init

A Wakeflow command for previewing and applying a new version 3 workspace setup. It can also reconfigure or reconcile an existing setup.

In plain words
What is it for?
Use it to initialize, reconfigure, reconcile, or recover a Wakeflow workspace while preserving the confirmed plan and avoiding automatic work dispatch.
Why use it?
It shows the exact planned changes and any blockers before making them, reducing the risk of applying an unintended workspace configuration.

Command

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 commands/gxfn/wakeflow/init
Clone the repo
git clone --depth 1 https://github.com/GxFn/Wakeflow
Per session 11 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 451 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 $0.00011 $0.00451
Opus 5 $0.00005 $0.00226
Sonnet 5 $0.00002 $0.00090
Haiku 4.5 $0.00001 $0.00045

Measured yesterday against content hash 4dd0be23b555, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

init 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 yesterday.

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/claude-code-wakeflow/commands/init.md · 41 lines

What it actually says

Initialize the current workspace with the public v3 maintenance owner.

  1. Build one explicit closed selection covering program, topology, storage, governance, and hosts. Repository/support/window entries link with request-local selectionKey; do not invent durable IDs or infer Design/Test from similar directory names.
  2. Call wakeflow_maintain_workspace with action: "fresh-initialize", mode: "preview", the workspace root, the complete selection, and the user's language. Preview is read-only.
  3. Show the user the exact managed surfaces, blockers, launchIntents, and confirmed plan boundary. Wait for explicit confirmation.
  4. Apply with the same root/action, mode: "apply", and the exact confirmedActionPlan plus confirmedActionPlanDigest returned by preview. Never reconstruct or edit the plan.
  5. If apply reports recovery-required, call the same action with mode: "recover", the exact plan/digest, and named operationId.
  6. Report created/verified surfaces and retained launch intents. Do not dispatch work from initialization.

An existing strict v3 workspace uses reconfigure for an intentional desired model change or reconcile to restore managed bytes/projections. There is no reset/discovery/useDiscovered alias. A recognized legacy workspace requires the explicit unregistered bootstrap path and separate user authorization; /init must not import or delete legacy state.

launchIntents are host-neutral authority. Route them through the packaged v3 Claude host facade's exact launch-window command, then register the final real session with wakeflow_register_window operation=register. Retired public-v2 window-host/thread-registry commands are not aliases. If the exact host effect or receipt is unavailable, report the intents and stop without writing substitute runtime.

If the Wakeflow MCP surface is unavailable, stop for plugin reload/reinstall; do not invoke backend scripts or cache paths directly.

$ARGUMENTS

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. yesterday First seen · 41 lines · 11 tokens per session scan A 4dd0be23b555

Subscribe to this mod's changes

init is a command published in the GitHub repository GxFn/Wakeflow (5 stars, last pushed 8d ago), licensed MIT. It adds 11 tokens to every session and 451 once invoked, about $0.0001 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.