stfu

stfu is a command for Claude Code from AR6420/Hail_Hydra. It costs 15 tokens per session (216 once invoked), scanned A, original, MIT.

A session command that tells dispatched helper agents to omit their intermediate explanations while keeping their final answers.

In plain words
What is it for?
It applies compressed internal communication to helper-agent tasks until the session ends, the mode is disabled, or another skill overrides it.
Why use it?
It reduces the amount of unused progress text produced during multi-agent work.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions subagents.

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/ar6420/hail_hydra/stfu
Clone the repo
git clone --depth 1 https://github.com/AR6420/Hail_Hydra

Made for: Claude Code.

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 stfu

README.md
[![agentmods](https://agentmods.dev/badge/commands/ar6420/hail_hydra/stfu.svg)](https://agentmods.dev/commands/ar6420/hail_hydra/stfu)
Your own site
<a href="https://agentmods.dev/commands/ar6420/hail_hydra/stfu"><img src="https://agentmods.dev/badge/commands/ar6420/hail_hydra/stfu.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 216 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 5.1 $0.00015 $0.00216
Opus 5 $0.00008 $0.00108
Sonnet 5 $0.00003 $0.00043
Haiku 4.5 $0.00002 $0.00022

Measured 6d ago against content hash 42927fa85914, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

stfu 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 6d 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.

content/commands/stfu.md · 22 lines

What it actually says

Hydra STFU Mode

Activate the STFU-Agents skill for this session.

Acknowledge with: "🐉 STFU-Agents mode activated. All dispatched subagents will run with compressed internal thinking. Final outputs unchanged. Run /skills to deactivate or say 'verbose agents'."

From this point in the session, when dispatching ANY subagent via the Task tool, prepend the internal-compression directive defined in skills/stfu-agents/SKILL.md to the task description.

Applies until:

  • Session ends
  • User says "verbose agents" / "stop STFU"
  • A conflicting skill is invoked

Why

Subagents generate intermediate prose that's billed by Anthropic but never read. Final summary is the only thing returned to Opus. STFU tells every dispatched subagent to skip narration — same final output, fewer billed tokens. Universal scope: any subagent in the session, regardless of source.

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. 6d ago First seen · 22 lines · 15 tokens per session scan A 42927fa85914

Subscribe to this mod's changes

stfu is a command published in the GitHub repository AR6420/Hail_Hydra (48 stars, last pushed 25d ago), licensed MIT. It adds 15 tokens to every session and 216 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 2026-08-30.