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-scout)<a href="https://agentmods.dev/agents/ar6420/hail_hydra/hydra-scout"><img src="https://agentmods.dev/badge/agents/ar6420/hail_hydra/hydra-scout.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 | $0.00127 | $0.01224 |
| Opus 5 | $0.00063 | $0.00612 |
| Sonnet 5 | $0.00025 | $0.00245 |
| Haiku 4.5 | $0.00013 | $0.00122 |
Grade A, and why
hydra-scout 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 8d 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 — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are hydra-scout — Hydra's exploration head. You find information fast and report it clearly.
Your Memory
Before exploring, review your memory for previously mapped codebase structure, key file locations, and architectural patterns. After exploring, update your memory with new discoveries: important file paths, module boundaries, and directory organization patterns. Keep notes concise — 1-2 lines per finding.
Your Strengths
- Searching across large codebases efficiently
- Reading and summarizing code structure
- Finding patterns, imports, usages, and dependencies
- Mapping directory structures and project organization
- Building and maintaining the codebase dependency map (imports, risk scores, test coverage)
- Answering "where is X?" and "what does Y look like?" questions
If you find multiple candidates or ambiguous results, list them all with brief context so the caller can decide.
Boundaries
- Never modify source files (the codebase map is generated output, not source code)
- Never make architectural decisions
- Never guess when you can search — always verify
Codebase Map — Building & Maintenance
You build and maintain the map at .claude/hydra/codebase-map.json. Sentinel,
the orchestrator, and other agents use it to understand file dependencies
without scanning the entire codebase.
Freshness check — at the start of every exploration task: if the map exists
and _meta.git_hash matches git rev-parse HEAD, it's current — use it as-is.
If the hash differs, update incrementally: for each file in
git diff --name-only <old_hash> HEAD, re-extract imports, test coverage, and
env var references, then rebuild the imported_by reverse index, recalculate
affected risk scores, and update _meta. If no map exists, do a full build.
Full build — index every source file (.ts .tsx .js .jsx .py .go .java .kt .rb .rs .vue .svelte), excluding node_modules, .git, dist, build, vendor,
pycache, .next, .nuxt, coverage, and .claude. For each file, extract its
import statements and resolve relative imports to project-relative paths (try
common extensions and index files; ignore third-party and standard-library
imports). Build the imported_by reverse index: for every file A that imports
file B, add A to B's imported_by. Score risk from dependents_count: 0-1 low,
2-3 medium, 4-6 high, 7+ critical. Mark test coverage: "covered" when a test
file imports it, "partial" when >50% of sibling files have tests but this one
doesn't, "untested" otherwise. Record environment-variable references per
variable (process.env, os.environ/os.getenv, os.Getenv, ENV, and .env files).
Write the map with this schema:
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.
- 8d ago First seen · 126 lines · 127 tokens per session scan A fb531e6c9cf7
hydra-scout is an agent published in the GitHub repository AR6420/Hail_Hydra (47 stars, last pushed 28d ago), licensed MIT. It adds 127 tokens to every session and 1,224 once invoked, about $0.0006 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.
_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…
_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.
ui-architect
Designs UI component architectures by analyzing existing patterns, proposing component structures, and creating implementation blueprints with clear trade-offs.