unattended

unattended is a command for coding agents from GxFn/Wakeflow. It costs 15 tokens per session (301 once invoked), scanned A, original, MIT.

A command for previewing a change between attended and unattended Claude operation. Attended operation asks for permission per action, while unattended operation allows host actions without those prompts.

In plain words
What is it for?
Use it to inspect the exact configuration change, confirm the risk, preview the plan, and apply only the approved workspace-specific change.
Why use it?
It prevents risky permission changes from being enabled without confirmation and checks that unattended access is limited to the intended workspace.

Command

Part of the wakeflow plugin — 3 skills, 7 commands, 1 MCP server shipped together

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/unattended
Clone the repo
git clone --depth 1 https://github.com/GxFn/Wakeflow

Or install wakeflow, the plugin that ships this one along with the rest of its 3 skills, 7 commands, 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 unattended

README.md
[![agentmods](https://agentmods.dev/badge/commands/gxfn/wakeflow/unattended.svg)](https://agentmods.dev/commands/gxfn/wakeflow/unattended)
Your own site
<a href="https://agentmods.dev/commands/gxfn/wakeflow/unattended"><img src="https://agentmods.dev/badge/commands/gxfn/wakeflow/unattended.svg" alt="Measured on agentmods" height="20"></a>
Per session 15 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 301 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 $0.00015 $0.00301
Opus 5 $0.00008 $0.00151
Sonnet 5 $0.00003 $0.00060
Haiku 4.5 $0.00002 $0.00030

Measured 5d ago against content hash add8686aeb9c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

unattended 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 5d 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/claude-code-wakeflow/commands/unattended.md · 29 lines

What it actually says

Changing Claude permission mode is an intentional desired-model change, not a helper-side config edit.

  1. Resolve on to the explicit unattended permission choice and off to the safe attended choice. If absent, ask the user.
  2. For on, require explicit confirmation that host actions may proceed without per-action prompts.
  3. Obtain the v3 Claude activation-scope observation. Only exact per-workspace coverage may be machine-verified. unknown or host-wide coverage blocks unattended activation; do not add a global workspace registry or extrapolate from one migrated workspace.
  4. Build the complete desired v3 selection and call wakeflow_maintain_workspace action=reconfigure mode=preview. Show the exact plan and wait for confirmation, then apply only that returned plan/digest.
  5. Window restarts/replacements are separate host effects through the v3 activation owner and typed binding tools. If that owner is unavailable, leave the config plan unapplied or report the post-apply activation blocker honestly; never use the public-v2 set-unattended/window-host writer.

Turning off does not require the extra risk confirmation but still follows the same preview/apply and exact-host-effect boundaries.

$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. 5d ago First seen · 29 lines · 15 tokens per session scan A add8686aeb9c

Subscribe to this mod's changes

unattended is a command published in the GitHub repository GxFn/Wakeflow (5 stars, last pushed 2d ago), licensed MIT. It adds 15 tokens to every session and 301 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.