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.
npx agentmods add skills/ar6420/hail_hydra/contentnpx skills add AR6420/Hail_Hydra --skill contentgit clone --depth 1 https://github.com/AR6420/Hail_HydraWrote 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.
[](https://agentmods.dev/skills/ar6420/hail_hydra/content)<a href="https://agentmods.dev/skills/ar6420/hail_hydra/content"><img src="https://agentmods.dev/badge/skills/ar6420/hail_hydra/content.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00083 | $0.06887 |
| Opus 5 | $0.00042 | $0.03444 |
| Sonnet 5 | $0.00017 | $0.01377 |
| Haiku 4.5 | $0.00008 | $0.00689 |
Grade A, and why
hydra 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 5d 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.
How it starts
The opening of the file, as written. The whole thing — 603 lines — stays where its author put it; the contents beside it link to each section on GitHub.
🐉 Hydra — Multi-Headed Speculative Execution
You are the orchestrator of a multi-agent toolkit: route substantial work to cheaper specialized heads, and keep your own reasoning for planning, verification, and genuinely hard problems.
Core Protocols
The sentinel scan is the safety guarantee that replaces the orchestrator re-reading every diff — run it after every code change.
Protocol 1: Sentinel Scan After Code Changes
When any agent returns output containing ⚠️ HYDRA_SENTINEL_REQUIRED,
dispatch hydra-sentinel-scan with the files and changes listed in the trigger
block — before presenting results to the user, before running any other agents.
This is blocking: the user does not see the code changes until sentinel completes.
Sequence:
- Receive agent output containing ⚠️ HYDRA_SENTINEL_REQUIRED
- Immediately dispatch hydra-sentinel-scan AND hydra-guard in parallel
- Wait for both to complete
- If sentinel-scan finds issues → dispatch hydra-sentinel (deep analysis)
- Wait for deep analysis
- Then present results to the user
If the agent output contains ✅ HYDRA_NO_CODE_CHANGES, skip sentinel. Present
results immediately.
Protocol 2: Sentinel Fix Decision Tree
When hydra-sentinel confirms real issues:
TRIVIAL (auto-fix without asking): Import renames, file path updates, barrel file re-exports. → Dispatch hydra-coder to fix. Re-run sentinel-scan to verify. → Tell user: "Sentinel caught [issue]. Auto-fixed."
MEDIUM (present to user, offer to fix): API contract mismatches, missing env vars, signature mismatches. → Show the sentinel report. Ask: "Want me to fix these?"
COMPLEX (report only): Architectural changes, migration needed, business logic decisions. → Show the report. Let user decide.
Response Compression — Orchestrator
Apply light compression to your responses: keep full grammar and natural prose, remove the waste. Done right, a careful reader notices responses are tighter and nothing sounds robotic.
What ships with it
25 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.
- agents/hydra-analyst.md 3.4 KB
- agents/hydra-coder.md 3.6 KB
- agents/hydra-git.md 2.8 KB
- agents/hydra-guard.md 3.9 KB
- agents/hydra-preflight.md 6.2 KB
- agents/hydra-runner.md 2.3 KB
- agents/hydra-scout.md 5.0 KB
- agents/hydra-scribe.md 2.2 KB
- agents/hydra-sentinel-scan.md 5.5 KB
- agents/hydra-sentinel.md 4.7 KB
- commands/guard.md 2.3 KB
- commands/help.md 2.3 KB
- commands/map.md 2.8 KB
- commands/preflight.md 3.2 KB
- commands/quiet.md 475 B
- commands/report.md 758 B
- commands/stats.md 7.2 KB
- commands/status.md 3.0 KB
- commands/stfu.md 1003 B
- commands/update.md 2.1 KB
- config/hydra.config.md 1.2 KB
- references/model-capabilities.md 6.3 KB
- references/routing-guide.md 12 KB
- skill-core.md 6.5 KB
- skills/stfu-agents/SKILL.md 2.6 KB
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.
- 5d ago First seen · 603 lines · 83 tokens per session scan A 1c3fafb6e012
hydra is a skill published in the GitHub repository AR6420/Hail_Hydra (48 stars, last pushed 25d ago), licensed MIT. It adds 83 tokens to every session and 6,887 once invoked, about $0.0004 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.
Other skills, from other repositories
azure-openai-to-responses
Migrate Python apps from Azure OpenAI Chat Completions to the Responses API. Covers AzureOpenAI/AsyncAzureOpenAI client migration to the v1 endpoint, streaming, tools, structured output, multi-turn, EntraID auth, and model compatibility checks. Python-focused, Azure OpenAI-specific. USE FOR: migrate to responses API…
natural-writing
Write like a human, not a language model. Use this skill whenever Claude is producing prose meant to be read by people.
gate-probe
Prove a gate before trusting it. Inventory violations, plant a defect, verify RED, restore GREEN, prevent idle scans, and confirm automatic wiring.
nx-workspace
Run and generate NX targets, configure project.json, and visualize dependency graphs. Use when you say: 'run affected tests', 'nx generate a library', 'configure project.json', or 'show dependency graph'.
playwright-testing
Playwright E2E testing patterns, cross-browser configuration, page objects, and CI setup. Use when creating E2E specs, visual regression suites, or configuring Playwright in CI. Trigger terms: playwright, e2e, trace, page object, cross-browser.
agent-memory
Creates, queries agent expertise profiles in AGENT-EXPERTISE.md; increments file-familiarity counters after each task; ranks candidate agents by recency, task-area match. Use when deciding which agent should handle a file, checking who last worked on a module, recording task outcomes, or assigning work based on past…