preflight

preflight is a command for coding agents from AR6420/Hail_Hydra. It costs 13 tokens per session (757 once invoked), scanned A, original, MIT.

A two-stage preflight check for a new or unfamiliar project. It first records the environment and project dependencies, then analyzes whether versions, tools, services, and hardware-related components are compatible.

In plain words
What is it for?
Use it before starting a project build to inspect runtime versions, installed packages, environment files, GPU and CUDA probes, build tools, and service connections.
Why use it?
It can reveal missing settings, broken GPU or CUDA setups, unavailable build tools, connectivity problems, and incompatible dependencies before a build fails later.

Command

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.

agentmods
npx agentmods add commands/ar6420/hail_hydra/preflight
Clone the repo
git clone --depth 1 https://github.com/AR6420/Hail_Hydra

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 preflight

README.md
[![agentmods](https://agentmods.dev/badge/commands/ar6420/hail_hydra/preflight.svg)](https://agentmods.dev/commands/ar6420/hail_hydra/preflight)
Your own site
<a href="https://agentmods.dev/commands/ar6420/hail_hydra/preflight"><img src="https://agentmods.dev/badge/commands/ar6420/hail_hydra/preflight.svg" alt="Measured on agentmods" height="20"></a>
Per session 13 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 757 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00013 $0.00757
Opus 5 $0.00006 $0.00378
Sonnet 5 $0.00003 $0.00151
Haiku 4.5 $0.00001 $0.00076

Measured 5d ago against content hash 41a31b2268c7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 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.

content/commands/preflight.md · 95 lines

How it starts

The opening of the file, as written. The whole thing — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Hydra Preflight

Run the two-phase environment and compatibility check before starting work on a new or unfamiliar project. Catches broken GPU stacks, missing env vars, and incompatible dependency pairs before they cost hours of debugging.

Execute the Preflight Protocol

Follow the Preflight Protocol defined in SKILL.md — two phases, always dispatched in sequence. Never skip Phase 2.

Phase 1 — Detection (dispatch hydra-preflight, Haiku 4.5)

Dispatch the hydra-preflight agent with this prompt:

Run a full preflight check on this project. Collect runtime versions, run all
GPU/CUDA probe scripts, inventory installed packages, compare .env.example
against .env, verify build tools exist, and check service connectivity. Return
the full structured PREFLIGHT_INVENTORY JSON. Do not make recommendations.

Wait for the agent to return PREFLIGHT_INVENTORY_COMPLETE before proceeding.

Phase 2 — Analysis (dispatch hydra-analyst, Sonnet 4.6)

Pass the full PREFLIGHT_INVENTORY from Phase 1 as context and dispatch hydra-analyst with this prompt:

You are performing a compatibility analysis on the following environment inventory.
Cross-reference all detected versions against known compatibility matrices.
Pay special attention to GPU stack combinations (PyTorch/CUDA/cuDNN),
framework pairs (React/Next, Python/TF), and Node/native addon combinations.

For each component or pair, return one of three verdicts:
  ✅ COMPATIBLE — versions are known-good together
  ⚠️  KNOWN RISK — this combination has known issues or is untested
  ❌ CONFIRMED BREAK — probe output or known matrix confirms incompatibility

For ❌ verdicts, include the specific fix (e.g. "pin pytorch==2.7.0").
For ⚠️  verdicts, include what to watch for.
For unknowns, flag as "UNVERIFIED — test before building" rather than assuming green.

Probe output from Phase 1 is ground truth — it always beats matrix knowledge.
If torch.cuda.is_available() returned False, that is a ❌ regardless of what
the version matrix says.

INVENTORY:
[paste full PREFLIGHT_INVENTORY here]

Read the full file on GitHub · 95 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. 5d ago First seen · 95 lines · 13 tokens per session scan A 41a31b2268c7

Subscribe to this mod's changes

preflight is a command published in the GitHub repository AR6420/Hail_Hydra (48 stars, last pushed 24d ago), licensed MIT. It adds 13 tokens to every session and 757 once invoked, about $0.0001 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.