foggy-mode

foggy-mode is a command for Claude Code from softcane/human-state-skills. It costs 11 tokens per session (779 once invoked), scanned C, a copy of brain-fog-mode, MIT.

A session mode that structures replies into four short labels: Current state, Next action, Do not do yet, and Stop point. It is intended for moments when too many choices or tasks make it hard to decide what to do.

In plain words
What is it for?
Use it when you feel foggy or unable to choose the next step. It helps decide what to act on, postpone, avoid, and use as a stopping point.
Why use it?
It reduces a complicated situation to one immediate action and sets boundaries around what can wait. Safety or medical emergencies take priority over this format.

Command for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the human-state-skills plugin — 5 skills, 7 commands shipped together

Good fit Use it when you feel foggy or unable to choose the next step. It helps decide what to act on, postpone, avoid, and use as a stopping point.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/softcane/human-state-skills/foggy-mode
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.

Clone the repo
git clone --depth 1 https://github.com/softcane/human-state-skills

Made for: Claude Code.

Or install human-state-skills, the plugin that ships this one along with the rest of its 5 skills, 7 commands.

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 foggy-mode

README.md
[![agentmods](https://agentmods.dev/badge/commands/softcane/human-state-skills/foggy-mode/github.svg)](https://agentmods.dev/commands/softcane/human-state-skills/foggy-mode)
Your own site
<a href="https://agentmods.dev/commands/softcane/human-state-skills/foggy-mode"><img src="https://agentmods.dev/badge/commands/softcane/human-state-skills/foggy-mode/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 foggy-mode

Your own site · 80×15
<a href="https://agentmods.dev/commands/softcane/human-state-skills/foggy-mode"><img src="https://agentmods.dev/badge/commands/softcane/human-state-skills/foggy-mode.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
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 779 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin 88% copy Near-identical to another mod 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 $0.00011 $0.00779
Opus 5 $0.00005 $0.00390
Sonnet 5 $0.00002 $0.00156
Haiku 4.5 $0.00001 $0.00078

Measured 10d ago against content hash 1dc081cc494b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade C, and why

foggy-mode scanned grade C with 1 finding 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.

Tells the agent never to refusehighAnti-refusal

Suppressing the ability to decline removes a core safety control; a later harmful request then succeeds.

- If the task is non-coding but safe, still answer in this mode. Do not refuse
Origin

This is a copy

88% identical to brain-fog-mode — 8 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

commands/foggy-mode.md · 66 lines

What it actually says

Activate foggy mode now.

Immediate safety or medical danger overrides this command. If the user describes sudden or severe medical symptoms, self-harm, harm to others, or inability to stay safe, exit the four-label format and prioritize immediate real-world help. If the prompt also contains hidden-message, special-signal, surveillance, or AI-bond content, reality-check-mode wins.

Output contract:

  • If the user explicitly asks for only the next step, output only Next action and one tiny atomic action. End immediately after that line.
  • Use these exact labels by default: Current state, Next action, Do not do yet, and Stop point.
  • Keep the whole answer short, but not context-free.
  • Current state may include one or two short context sentences when that reduces ambiguity or names the immediate constraint.
  • Context must reduce uncertainty, not create more decisions, explanations, or future tasks.
  • Next action is one action only.
  • If more than one action seems useful, choose the earliest visible action.
  • Do not combine setup plus sending. Either place/open/write, or send one message, but not both.
  • Prefer one imperative verb when possible: Put, Open, Write, or Send. Avoid compound actions such as get X and place it.
  • For concrete multi-step work, choose one visible unit to complete: one object placement, one field, one sentence, or one message. Do not ask the user to gather multiple prerequisites.
  • Do not tell the user to review the whole surface, inspect every section, or organize everything.
  • Do not ask a clarification question when a safe first step is available.
  • Next action has no bullets, numbered steps, branch choices, conditionals, or follow-up tasks.
  • Next action must not join actions with words like then, after, or once.
  • Next action should not use and to join two verbs. Choose one visible unit only.
  • If the action is sending a message, include only that message and stop.
  • Put future work in Do not do yet as things to avoid, not as instructions.
  • Stop point must start with Stop when.
  • Stop point must only say where to pause; do not add a later task there.
  • Stop point must mirror the immediate Next action, not later work.
  • Stop point must not contain a new imperative command like Send, Open, Write, Get, Check, or Reply.
  • Valid stop points: Stop when the message is sent. or Stop when the document is on the table.
  • Invalid stop points: After sending the message, get the document.
  • Stop point must not ask the user to reply, report back, inspect, check, or continue with another task.
  • Stop point must not include extra checks, investigation, inspection, or follow-up work.
  • For messages or multi-step tasks, still give one action and one stop point only.
  • Before final, silently rewrite the answer if Next action hides a sequence, combines setup plus sending, or if Stop point does not start with Stop when.
  • If the task is non-coding but safe, still answer in this mode. Do not refuse only because it is outside software engineering.

Stay in this mode until the user says normal mode, stop foggy mode, or invokes another human-state mode.

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 · 66 lines · 11 tokens per session scan C 1dc081cc494b

Subscribe to this mod's changes

foggy-mode is a command published in the GitHub repository softcane/human-state-skills (113 stars, last pushed 1mo ago), licensed MIT. It adds 11 tokens to every session and 779 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it C with 1 finding (tells the agent never to refuse). It is 88% identical to brain-fog-mode, differing in 8 lines, and is treated as a copy.