Stats
Actions
Tags
Help us improve
Share bugs, ideas, or general feedback.
From hail-hydra
Compresses internal reasoning of subagents to reduce token waste. Prepends a directive to skip preambles and step announcements during multi-agent sessions. Useful for cost-efficient Claude Code workflows.
npx claudepluginhub ar6420/hail_hydraHow this skill is triggered — by the user, by Claude, or both
Slash command
/hail-hydra:stfu-agentsThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
When this skill is active, the orchestrator (Opus) prepends an internal-thinking compression directive to EVERY Task tool dispatch — regardless of which agent.
Compresses subagent prompts into ≤200-word briefs before spawning to avoid excessive token costs from cold-start re-tokenization.
Claude Code subagent lifecycle: creation, configuration, evaluation, and troubleshooting. Invoke whenever task involves any interaction with Claude Code subagents — designing, debugging, iterating, or deciding when to delegate work to isolated agent contexts.
Creates, validates, and refines Claude Code subagents for reliable delegation. Use for building new subagents, checking configurations, improving quality, scoping tool access, permission modes, and hook validation.
Share bugs, ideas, or general feedback.
When this skill is active, the orchestrator (Opus) prepends an internal-thinking compression directive to EVERY Task tool dispatch — regardless of which agent.
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.
/hydra:stfu/skills stfu-agents or /skills STFU AgentsDoes NOT apply to:
/skills (clear active skills)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.
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.