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 skills add AR6420/Hail_Hydra --skill copilotgit 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/copilot)<a href="https://agentmods.dev/skills/ar6420/hail_hydra/copilot"><img src="https://agentmods.dev/badge/skills/ar6420/hail_hydra/copilot/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.
<a href="https://agentmods.dev/skills/ar6420/hail_hydra/copilot"><img src="https://agentmods.dev/badge/skills/ar6420/hail_hydra/copilot.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00030 | $0.01111 |
| Opus 5.5 | $0.00012 | $0.00444 |
| Sonnet 5.5 | $0.00006 | $0.00222 |
| Haiku 4.5 | $0.00003 | $0.00111 |
Grade A, and why
hail-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 27d 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 — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Hail Hydra for GitHub Copilot CLI
Activation boundary
Loading this file or calling a skill tool is not activation. Require an explicit /hail-hydra request in the current user input, not prior history.
Without it, do not load roles, run helpers or delegate under Hydra — these are instruction gates, not a host lock.
On each subsequent user message, check again: without an explicit /hail-hydra invocation, use the normal agent.
With no task, show a short usage example without starting agents.
Stay in this session, directory, authentication and permissions. Use native subagents only.
Never launch another AI CLI (copilot, agency, claude, gemini, codex), API client or orchestration provider for the task.
Do not bypass permissions, send code to another provider, install hooks or global instructions, pin a persistent agent/model, or enable autopilot.
Explicit utilities
For leading flags, read the command guide; unknown flags get usage, not execution.
Cost, speed and context first
Preserve correctness while balancing mode priorities: cost, elapsed time and context. Every dispatch must plausibly repay overhead through parallel progress, a cheaper capable model or context isolation; otherwise work directly. Group tiny related steps; avoid per-edit dispatch.
Reuse verified findings and decisions; give each worker only its relevant context slice, not the full conversation.
Plan from the goal
Derive acceptance criteria and select specialists from the goal and project; do not require agent names, a swarm flag or repeated "continue" prompts. Keep a compact task ledger with dependencies, file ownership, decisions and evidence in the conversation/task tracker, not new repository planning files. For substantial work, follow context continuity: save session-local checkpoints and restore verified decisions after compaction. Subagents have separate contexts; pass relevant main-conversation facts.
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.
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.
- 27d ago First seen · 93 lines · 30 tokens per session scan A b882af5f066c
hail-hydra is a skill published in the GitHub repository AR6420/Hail_Hydra (49 stars, last pushed 4d ago), licensed MIT. It adds 30 tokens to every session and 1,111 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-09-19.
Other skills, from other repositories
creating-commit
Creates context-aware git commits with smart pre-commit checks, submodule support, and conventional commit message generation. Use when user requests to commit changes, stage and commit, check in code, save work, save changes, push my code, finalize changes, add to git, create commits, run /commit command, or mentions…
cleaning-up-branches
Deletes merged git branches (local and remote) and flags stale unmerged branches for manual review. Use when user mentions "cleanup branches", "delete merged branches", "prune old branches", "remove stale branches", "branch cleanup", or runs /cleanup-branches command.
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…
doc-freshness
Detect documentation drift, stale references, and cross-document inconsistencies in any project. Scans for code-doc drift (API/function changes not reflected in docs), cross-doc drift (conflicting information across documents), and stale references (broken links, deleted files, outdated versions). Use when checking…
rfc
Manage architecture RFCs: create, review, list, update, and transition status. Use when user mentions "RFC", "technical proposal", "architecture proposal", or wants to draft, review, list, update, or change status of RFCs.
listing-stale-branches
Lists local and remote git branches that are candidates for cleanup — merged but not deleted, and inactive branches with no commits in a configurable period (default 3 months). Use when user mentions "stale branches", "old branches", "branch cleanup", "prune branches", "dead branches", "unused branches", "inactive…