STFU Agents

STFU Agents is a skill for Claude Code, Codex from AR6420/Hail_Hydra. It costs 63 tokens per session (605 once invoked), scanned A, original, MIT.

Session instructions that shorten the hidden reasoning of subagents before they report results. Subagents are smaller agents dispatched by a main coding agent to perform parts of a task.

In plain words
What is it for?
Use them when dispatching subagents during a session, including Hydra, third-party, or built-in Claude Code agents.
Why use it?
They reduce internal work that the main agent does not need to see, which can make delegated work use fewer context tokens.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions subagents; mentions Claude Code.

Good fit Use them when dispatching subagents during a session, including Hydra, third-party, or built-in Claude Code agents.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ar6420/hail_hydra/stfu-agents
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.

Any agent
npx skills add AR6420/Hail_Hydra --skill stfu-agents
Clone the repo
git clone --depth 1 https://github.com/AR6420/Hail_Hydra

Made for: Claude Code, Codex.

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 Agents

README.md
[![agentmods](https://agentmods.dev/badge/skills/ar6420/hail_hydra/stfu-agents/github.svg)](https://agentmods.dev/skills/ar6420/hail_hydra/stfu-agents)
Your own site
<a href="https://agentmods.dev/skills/ar6420/hail_hydra/stfu-agents"><img src="https://agentmods.dev/badge/skills/ar6420/hail_hydra/stfu-agents/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 STFU Agents

Your own site · 80×15
<a href="https://agentmods.dev/skills/ar6420/hail_hydra/stfu-agents"><img src="https://agentmods.dev/badge/skills/ar6420/hail_hydra/stfu-agents.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 63 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 605 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00063 $0.00605
Opus 5 $0.00032 $0.00302
Sonnet 5 $0.00013 $0.00121
Haiku 4.5 $0.00006 $0.00060

Measured 10d ago against content hash 0c462b702504, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

STFU Agents 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 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.

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/skills/stfu-agents/SKILL.md · 60 lines

How it starts

The opening of the file, as written. The whole thing — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.

STFU-Agents Mode

When this skill is active, the orchestrator (Opus) prepends an internal-thinking compression directive to EVERY Task tool dispatch — regardless of which agent.

Behavior — Orchestrator (Opus)

When dispatching any subagent via the Task tool, prepend this directive to the prompt argument:

[INTERNAL-COMPRESSION DIRECTIVE — STFU-Agents mode active]
Your internal reasoning is billed but never read — only your final summary returns to the orchestrator. Therefore:
1. Skip preambles ("Let me…", "I'll examine…", "First I need to…")
2. Skip step announcements ("Step 1:", "Now let me…")
3. Skip transition prose between tool calls
4. Skip restatements of tool outputs (they're already in your context)
5. Act first, summarize at the end
Maintain whatever output format your role requires. Just keep the path from task → output terse internally.

Activation

  • /hydra:stfu
  • /skills stfu-agents or /skills STFU Agents
  • Natural language: "STFU agents", "shut up agents", "quiet agents", "compress all agents"

Scope

  • Hydra's own subagents (already have Tier 3 — harmless reinforcement)
  • Third-party subagents installed by the user
  • Claude Code's built-in subagents (Explore, etc.)
  • User-defined custom subagents

Does NOT apply to:

  • The main orchestrator (Opus) — orchestrator follows SKILL.md's own response rules
  • Direct user-facing responses

Deactivation

  • /skills (clear active skills)
  • Natural language: "verbose agents", "stop STFU"

When NOT to use

  • Debugging a subagent's behavior (you want to see its reasoning)
  • Teaching the user how subagents work
  • User explicitly asked for verbose mode

Compatibility

Purely additive at runtime. No agent files modified. If a subagent ignores the directive, no harm done — falls back to baseline. Coexists with any other skill or framework.

Risk Disclosure

STFU-Agents adds a directive to subagents Hydra does not own. While the directive is additive and harmless in principle, it has not been tested against every possible subagent definition. Activate explicitly; deactivate if anything looks off.

Read the full file on GitHub · 60 lines

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 · 60 lines · 63 tokens per session scan A 0c462b702504

Subscribe to this mod's changes

STFU Agents is a skill published in the GitHub repository AR6420/Hail_Hydra (47 stars, last pushed 1mo ago), licensed MIT. It adds 63 tokens to every session and 605 once invoked, about $0.0003 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.

Related

Other skills, from other repositories

quality-stack

Scan a project to detect configured quality and testing tools across JVM (Gradle/Maven), Android (AGP/Compose/KMP), Node.js/TypeScript, and Python ecosystems. Cross-reference against research-backed recommendations and assist with setup. Auto-detects project type(s) including monorepos with mixed ecosystems. Use when…

joaquimscosta/arkhe-claude-plugins · 148 tokens

lyra

Transform vague inputs into precision-optimized AI prompts for Claude, ChatGPT, Gemini, or other LLMs. Use when user mentions "optimize prompt", "improve prompt", "lyra", "prompt engineering", or needs help crafting effective AI prompts.

joaquimscosta/arkhe-claude-plugins · 56 tokens

prototype

Rapid UI prototyping — generates 3 visually distinct HTML/CSS components from a text prompt and serves them in a live browser gallery. Use when user runs /prototype, asks to "prototype a UI", "mock up a component", "generate HTML mockups", "create UI variations", "design exploration", "quick UI concept", or wants to…

joaquimscosta/arkhe-claude-plugins · 118 tokens

deep-research

Deep research on technical topics using EXA tools with intelligent two-tier caching. Use when user asks to research a topic, investigate best practices, look up information, find patterns, or explore architectures. Also invoked by /research command. Triggers: "research", "look up", "investigate", "deep dive", "find…

joaquimscosta/arkhe-claude-plugins · 86 tokens

sops-add-key

Add a new machine's age public key to .sops.yaml and re-encrypt all files. Use for multi-machine setups. Use when user mentions "add key", "add machine", "sops add key", "new machine", "authorize machine", "share key", "add public key", "multi machine sops".

joaquimscosta/arkhe-claude-plugins · 72 tokens

taskfile-setup

Install Taskfile (task) and scaffold or audit Taskfile.yml configurations with ecosystem-aware templates. Auto-detects Node.js/pnpm, JVM/Gradle, Python/uv, Docker, and recommends single-file or multi-file (includes) patterns based on project complexity. Use when user runs /devtools:taskfile-setup, mentions "taskfile…

joaquimscosta/arkhe-claude-plugins · 110 tokens