hydra-preflight

hydra-preflight is an agent for Claude Code from AR6420/Hail_Hydra. It costs 63 tokens per session (1,764 once invoked), scanned A, original, MIT.

A preflight agent that checks a new or unfamiliar project before coding begins. It records installed programming-language versions, version files, declared requirements and the project's dependency tree.

In plain words
What is it for?
Use it to inventory a project's environment, runtimes, version constraints and dependencies when starting work or investigating setup problems.
Why use it?
It exposes missing tools and compatibility details early, before they cause confusing build or runtime failures.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: model in frontmatter.

Good fit Use it to inventory a project's environment, runtimes, version constraints and dependencies when starting work or investigating setup problems.

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

Clone the repo
git clone --depth 1 https://github.com/AR6420/Hail_Hydra

Made for: Claude Code.

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-preflight

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

Your own site · 80×15
<a href="https://agentmods.dev/agents/ar6420/hail_hydra/hydra-preflight"><img src="https://agentmods.dev/badge/agents/ar6420/hail_hydra/hydra-preflight.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 63 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,764 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.
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 $0.01764
Opus 5.5 $0.00025 $0.00706
Sonnet 5.5 $0.00013 $0.00353
Haiku 4.5 $0.00006 $0.00176

Measured 1mo ago against content hash 0a6efa6c9c04, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

hydra-preflight 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 1mo 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/agents/hydra-preflight.md · 184 lines

How it starts

The opening of the file, as written. The whole thing — 184 lines — stays where its author put it; the contents beside it link to each section on GitHub.

hydra-preflight

You are the preflight detection head: collect facts, run probes, and return a structured inventory — no judgment or recommendations; the analyst handles compatibility reasoning.

Your Task

Run every check; the inventory is only useful complete. Report every finding, including nulls and failures — a missing value is as important as a present one.


1. Runtime Versions

Detect and record the exact installed version of every runtime present:

node --version 2>/dev/null || echo "NOT_FOUND"
python --version 2>/dev/null || python3 --version 2>/dev/null || echo "NOT_FOUND"
python -c "import sys; print(sys.version_info)" 2>/dev/null || echo "NOT_FOUND"
bun --version 2>/dev/null || echo "NOT_FOUND"
deno --version 2>/dev/null || echo "NOT_FOUND"
ruby --version 2>/dev/null || echo "NOT_FOUND"
go version 2>/dev/null || echo "NOT_FOUND"
rustc --version 2>/dev/null || echo "NOT_FOUND"
java -version 2>/dev/null || echo "NOT_FOUND"

Also check for version lock files and declared version requirements:

cat .nvmrc 2>/dev/null || echo "NO_NVMRC"
cat .python-version 2>/dev/null || echo "NO_PYTHON_VERSION"
cat .tool-versions 2>/dev/null || echo "NO_TOOL_VERSIONS"
cat package.json 2>/dev/null | grep -A5 '"engines"' || echo "NO_ENGINES_FIELD"

2. Package Manager and Dependencies

# Node
ls node_modules 2>/dev/null | wc -l || echo "node_modules: NOT_FOUND"
cat package.json 2>/dev/null | grep -E '"dependencies"|"devDependencies"' | head -5

# Python
pip list 2>/dev/null | head -30 || pip3 list 2>/dev/null | head -30 || echo "pip: NOT_FOUND"
cat requirements.txt 2>/dev/null || cat requirements/*.txt 2>/dev/null || echo "NO_REQUIREMENTS"
cat pyproject.toml 2>/dev/null | head -40 || echo "NO_PYPROJECT"
ls -la venv/ 2>/dev/null || ls -la .venv/ 2>/dev/null || echo "NO_VENV"

# Others
cat Cargo.toml 2>/dev/null | head -20 || echo "NO_CARGO"
cat go.mod 2>/dev/null | head -10 || echo "NO_GOMOD"
cat Gemfile 2>/dev/null | head -10 || echo "NO_GEMFILE"

Read the full file on GitHub · 184 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. 1mo ago Changed · +1 lines 0a6efa6c9c04
  2. 2mo ago First seen · 183 lines · 63 tokens per session scan A 08aa41b02c39

Subscribe to this mod's changes

hydra-preflight is an agent published in the GitHub repository AR6420/Hail_Hydra (51 stars, last pushed 6d ago), licensed MIT. It adds 63 tokens to every session and 1,764 once invoked, about $0.0003 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 2026-08-30.

Related

hydra-preflight compared with agents from other repositories

hydra-preflight next to 6 agents from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
hydra-preflightAR6420/Hail_HydraAgent516d agoMITA63Claude Code
spring-boot-upgrade-verifierjoaquimscosta/arkhe-claude-pluginsAgent2222d agoMITA74Claude Code
ralph-agentjoaquimscosta/arkhe-claude-pluginsAgent2222d agoMITA52Claude Code
spring-boot-reviewerjoaquimscosta/arkhe-claude-pluginsAgent2222d agoMITA66Claude Code
ui-architectjoaquimscosta/arkhe-claude-pluginsAgent2222d agoMITA27Claude Code
system-architectjoaquimscosta/arkhe-claude-pluginsAgent2222d agoMITA64Claude Code
code-reviewerluiseiman/dotforgeAgent83d agoMITA42Claude Code