agentmods.dev

hydra

hydra is a skill for Claude Code from Kasempiternal/Claude-Agent-System. It costs 33 tokens per session (5,563 once invoked), scanned B, original, MIT.

A coordinator for splitting several independent coding tasks among Claude agents, planning them together, and running them in safe parallel waves.

In plain words
What is it for?
Use it when multiple tasks need to be completed at once across a codebase and some tasks may touch overlapping files.
Why use it?
Joint planning helps identify file conflicts before agents edit the same project, while dependencies determine which tasks can run together.

Skill for Claude Code

Written for Claude Code: argument-hint in frontmatter. Also seen: model in frontmatter; reads .claude/ paths; names the AskUserQuestion tool.

Part of the cas plugin — 19 skills, 3 hooks, 2 MCP servers shipped together

not rated 15repo 1mo ago B scan 33 tokens original MIT

Good fit Use it when multiple tasks need to be completed at once across a codebase and some tasks may touch overlapping files.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/kasempiternal/claude-agent-system/hydra
View source ↗ Kasempiternal/Claude-Agent-System kasempiternal.github.io
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 Kasempiternal/Claude-Agent-System --skill hydra
Clone the repo
git clone --depth 1 https://github.com/Kasempiternal/Claude-Agent-System

Made for: Claude Code.

Or install cas, the plugin that ships this one along with the rest of its 19 skills, 3 hooks, 2 MCP servers.

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 hydra

README.md
[![agentmods](https://agentmods.dev/badge/skills/kasempiternal/claude-agent-system/hydra.svg)](https://agentmods.dev/skills/kasempiternal/claude-agent-system/hydra)
Your own site
<a href="https://agentmods.dev/skills/kasempiternal/claude-agent-system/hydra"><img src="https://agentmods.dev/badge/skills/kasempiternal/claude-agent-system/hydra.svg" alt="Measured on agentmods" height="20"></a>
Per session 33 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,563 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00033 $0.05563
Opus 5 $0.00016 $0.02781
Sonnet 5 $0.00007 $0.01113
Haiku 4.5 $0.00003 $0.00556

Measured 7d ago against content hash ea89997471e5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade B, and why

hydra scanned grade B 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 7d 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

Read `~/.claude/settings.json`. Verify `env.CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS` is `"1"`.
claude-agent-system-plugin/skills/hydra/SKILL.md · 498 lines

How it starts

The opening of the file, as written. The whole thing — 498 lines — stays where its author put it; the contents beside it link to each section on GitHub.

██╗  ██╗██╗   ██╗██████╗ ██████╗  █████╗
██║  ██║╚██╗ ██╔╝██╔══██╗██╔══██╗██╔══██╗
███████║ ╚████╔╝ ██║  ██║██████╔╝███████║
██╔══██║  ╚██╔╝  ██║  ██║██╔══██╗██╔══██║
██║  ██║   ██║   ██████╔╝██║  ██║██║  ██║
╚═╝  ╚═╝   ╚═╝   ╚═════╝ ╚═╝  ╚═╝╚═╝  ╚═╝

            ⚔ Multi-Head Swarm ⚔
          CLAUDE AGENT SYSTEM

MANDATORY: Output the banner above verbatim as your very first message to the user, before any tool calls or other output.

You are entering HYDRA ORCHESTRATOR MODE. You are Opus, the multi-headed orchestrator. You coordinate N independent tasks simultaneously — planning them together to detect file conflicts, then executing in parallel waves where safe, and sequentially where files overlap.

This is the HYDRA EDITION: Multiple tasks are analyzed holistically, conflicts are resolved at plan time, and implementation swarms deploy in dependency-ordered waves using Agent Teams.

Hydra is an explicit, deterministic alternative to Claude Dynamic Workflows. Once invoked, Hydra owns decomposition, planning, team creation, wave execution, and verification. Do not hand the request to a dynamic workflow, /zk, /systemcc, or another router.

Your Role: Multi-Task Orchestrator

  • You are the BRAIN, not the HANDS — delegate everything via Task tool with team_name
  • Create a team, spawn teammates for actual work
  • Use the shared task list (TaskCreate/TaskUpdate/TaskList) to track all N tasks across waves
  • Use SendMessage to coordinate teammates and relay context between waves
  • Maximize parallelization ACROSS tasks, not just within them
  • NEVER implement code directly

Phase 0: Prerequisites Check

Step 0: Enforce Delegation Mode Exclusivity

Inspect the current conversation for the latest explicit /gpt-architect on or /gpt-architect off command. New sessions default to OFF.

  • If the latest command is /gpt-architect on: STOP before calling Agent, TeamCreate, or any workflow router. Tell the user: 
    HYDRA needs Claude Agent Teams, but GPT Architect currently reserves all delegation for Codex.
Run /gpt-architect off, then invoke /hydra again.
  • If OFF or never enabled: continue.

Read the full file on GitHub · 498 lines

Files

What ships with it

8 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 7d ago First seen · 498 lines · 33 tokens per session scan B ea89997471e5

Subscribe to this mod's changes

hydra is a skill published in the GitHub repository Kasempiternal/Claude-Agent-System (15 stars, last pushed 1mo ago), licensed MIT. It adds 33 tokens to every session and 5,563 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Claude CodeCode reviewPlanningai-agentsautomationclaudeclaude-code-plugin
Related

Other skills, from other repositories

review

Review code with parallel agents — tests, security, Ecto, LiveView, Oban. Use after implementation to catch bugs and anti-patterns before committing.

oliver-kriska/claude-elixir-phoenix · 34 tokens

audit

Project health audit and health check — architecture, performance, tests, dependencies, code quality. Use when assessing overall project health, before releases, or after refactors.

oliver-kriska/claude-elixir-phoenix · 35 tokens

pr-review

Address feedback left on a GitHub pull request: fetch unresolved review threads, make agreed Elixir/Phoenix code fixes, reply, and resolve. Use for a PR URL/number or reviewer comments. NOT for pre-PR review, findings triage, or CI monitoring.

oliver-kriska/claude-elixir-phoenix · 59 tokens

phx-pr-review

Address feedback left on a GitHub pull request: fetch unresolved review threads, make agreed Elixir/Phoenix code fixes, reply, and resolve. Use for a PR URL/number or reviewer comments. NOT for pre-PR review, findings triage, or CI monitoring.

oliver-kriska/claude-elixir-phoenix · 61 tokens

boundaries

Analyze Phoenix context boundaries and module coupling via mix xref. Use when checking cross-context calls, validating dependencies, before splitting modules, or reviewing architecture.

oliver-kriska/claude-elixir-phoenix · 33 tokens

challenge

Challenge mode reviews - rigorous questioning before approving changes. Use when you want thorough scrutiny of Ecto changes, LiveView events, OTP designs, or PR readiness.

oliver-kriska/claude-elixir-phoenix · 34 tokens