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.
git 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/agents/ar6420/hail_hydra/hydra-preflight)<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="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 | $0.00063 | $0.01758 |
| Opus 5 | $0.00032 | $0.00879 |
| Sonnet 5 | $0.00013 | $0.00352 |
| Haiku 4.5 | $0.00006 | $0.00176 |
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 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.
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 — 183 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"
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.
- 7d ago First seen · 183 lines · 63 tokens per session scan A 08aa41b02c39
hydra-preflight is an agent published in the GitHub repository AR6420/Hail_Hydra (48 stars, last pushed 26d ago), licensed MIT. It adds 63 tokens to every session and 1,758 once invoked, about $0.0003 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 agents, from other repositories
_security
Senior Security Engineer that performs threat modeling, auth audits, code security reviews, and launch sign-off. Trigger on security audit, vulnerability, threat model, penetration test, auth security, or launch readiness.
_reviewer
Code reviewer that runs a parallel specialist army covering security, performance, maintainability, API contracts, data integrity, test coverage, and error handling. Trigger on code review, review, PR review, pull request, or review army.
_mobile
Senior Mobile Engineer for React Native and Expo. Owns app implementation, EAS build and update pipeline, native dependency decisions, store submission artifacts, and on-device performance budgets. Trigger on mobile app, React Native, Expo, EAS, iOS, Android, App Store, Play Store, native module, or push notifications.
_critic
Plan critic. Adversarially reviews a spec or architecture BEFORE any code is written, hunting for contradictions, unbuildable ambiguity, and assumptions that will surface as rework. Runs as a gate between design and build. Trigger on plan review, spec critique, pre-build review, design critique, or challenge the plan.
_privacy
Privacy Engineer specializing in reidentification risk, data minimization, retention enforcement, and anonymity architecture. Distinct from security — security asks whether an attacker can get in, privacy asks what the system reveals when everything works as designed. Trigger on anonymity, pseudonymity…
ui-architect
Designs UI component architectures by analyzing existing patterns, proposing component structures, and creating implementation blueprints with clear trade-offs.