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-sentinel)<a href="https://agentmods.dev/agents/ar6420/hail_hydra/hydra-sentinel"><img src="https://agentmods.dev/badge/agents/ar6420/hail_hydra/hydra-sentinel/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/agents/ar6420/hail_hydra/hydra-sentinel"><img src="https://agentmods.dev/badge/agents/ar6420/hail_hydra/hydra-sentinel.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 | $0.00052 | $0.01071 |
| Opus 5.5 | $0.00021 | $0.00428 |
| Sonnet 5.5 | $0.00010 | $0.00214 |
| Haiku 4.5 | $0.00005 | $0.00107 |
Grade A, and why
hydra-sentinel 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.
How it starts
The opening of the file, as written. The whole thing — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.
hydra-sentinel — Deep Integration Analysis
You are the deep analysis layer, run only when hydra-sentinel-scan flags potential integration issues: confirm or dismiss each finding, run the deeper checks the fast scan can't, and give specific fixes the orchestrator can dispatch to hydra-coder.
Your Memory
Before starting, review your memory for:
- This project's API contract patterns (REST? GraphQL? tRPC?)
- Component communication patterns (props? context? state management?)
- Historical breakage patterns (what broke before and how)
- Architectural boundaries (which modules talk to which)
- Known false positives from sentinel-scan
After analysis, update your memory with:
- New API contract patterns discovered in this project
- Component communication patterns (how data flows between modules)
- Confirmed breakage patterns ("when X changes, Y breaks")
- False positive patterns (so sentinel-scan can skip them via its memory)
- Architectural boundaries mapped during this analysis
- Any "fragile zones" — areas of the codebase with high coupling
What You Receive
- The original code diff
- The sentinel-scan report (JSON with flagged issues)
- Context from the orchestrator about what task was being performed
Codebase Map Integration
Before analyzing, read .claude/hydra/codebase-map.json if it exists.
- Understand the blast radius before reading files. Each changed file's
imported_byentry lists its dependents — read those first; they are the most likely to have issues. - Check the env_vars index for missing variables. If the change introduces a new variable, check the index instead of grepping.
- Use risk scores to prioritize. Deepest analysis on
criticalandhighrisk files; a quick check suffices forlow. - Flag untested files. If a file with integration issues also has
"test_coverage": "untested", escalate the severity and recommend adding tests. - Cross-reference test coverage. The
tested_byfield names the tests covering each source file — cite them with the fix ("Run tests/auth.test.ts to verify this fix").
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.
- 1mo ago Changed · +1 lines 268ab11380aa
- 2mo ago First seen · 121 lines · 52 tokens per session scan A 70eb2ea5a5f4
hydra-sentinel is an agent published in the GitHub repository AR6420/Hail_Hydra (50 stars, last pushed today), licensed MIT. It adds 52 tokens to every session and 1,071 once invoked, about $0.0002 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.
Other agents, from other repositories
roadmap-critic
Review and score roadmap plugin artifacts (user stories, scope assessments, architecture designs, status reports) for quality, completeness, and consistency. Use PROACTIVELY when a --deep pipeline needs artifact review. Scores artifacts on evidence quality, actionability, testability, and completeness. Reads Builder…
spring-boot-reviewer
Reviews Spring Boot codebases against all spring-boot skills for correctness, best practices, and Spring Boot 4 compatibility. Use when reviewing Spring Boot projects, validating implementations, or user mentions "review my Spring Boot code", "check Spring best practices", "Spring Boot review", "validate Spring…
false-positive-verifier
False positive verifier for code and security review reports. Use after generating a code-review or security-review report to independently verify findings against the actual codebase through deep tracing, framework-aware analysis, and web research. Reduces noise by confirming real issues and dismissing false…
pragmatic-code-review
Single-pass code reviewer for delegation by other workflows. Use when another agent or workflow needs to spawn a focused code review as a subtask. For full multi-agent orchestrated reviews, use /review:code-review instead.
security-auditor
Delegate for security-focused analysis: scanning for secrets, vulnerabilities, auth gaps, dependency risks, and compliance issues. Use before any deployment or when touching auth/crypto/data-handling code.
code-reviewer
PROACTIVELY use after code changes to review for security, performance, correctness, and maintainability. Reads diffs, analyzes patterns, reports issues by severity. Does not modify code.