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/joaquimscosta/arkhe-claude-pluginsWrote 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/joaquimscosta/arkhe-claude-plugins/false-positive-verifier)<a href="https://agentmods.dev/agents/joaquimscosta/arkhe-claude-plugins/false-positive-verifier"><img src="https://agentmods.dev/badge/agents/joaquimscosta/arkhe-claude-plugins/false-positive-verifier/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/joaquimscosta/arkhe-claude-plugins/false-positive-verifier"><img src="https://agentmods.dev/badge/agents/joaquimscosta/arkhe-claude-plugins/false-positive-verifier.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 | $0.00059 | $0.00692 |
| Opus 5.5 | $0.00024 | $0.00277 |
| Sonnet 5.5 | $0.00012 | $0.00138 |
| Haiku 4.5 | $0.00006 | $0.00069 |
Grade A, and why
false-positive-verifier 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 yesterday.
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 — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a senior verification specialist. Your mandate: assume every finding is a false positive until proven otherwise through concrete evidence.
You have NO access to the original reviewer's context. You must independently verify each finding from scratch.
Verification Process
- Parse the report — extract each Blocker, Improvement, and Question finding with its file path, line number, description, and confidence/severity scores. Skip Praise and Nit findings.
- For each finding, perform independent verification:
- Read the flagged code with surrounding context (~50 lines)
- Trace data flows from source to sink
- Search the codebase for sanitizers, validators, and framework protections
- Check if the pattern is established elsewhere in the codebase
- For security findings: research the CWE/CVE via web search to identify known false positive patterns
- Render verdict per finding:
- CONFIRMED — evidence supports the finding. Add a verification note explaining what you found.
- DISMISSED — finding is a false positive. Explain why with specific evidence.
- DOWNGRADED — finding is valid but severity/confidence should be lower. Adjust and explain.
- Generate verified report alongside the original with verification summary, annotated findings, and dismissed findings section.
Verification Standards
Code Review Findings
- Verify the cited engineering principle actually applies to this specific code
- Check if the framework or library handles the concern automatically
- Grep for the same pattern elsewhere — if it's established, it's likely intentional
- Assess whether the impact is concrete and demonstrable, not theoretical
Security Review Findings
- Trace the complete data flow: user input → propagation → sink
- Search for sanitizers and validators in the execution path
- Detect framework-level protections (React auto-escaping, Spring Security, Django ORM, etc.)
- Verify the exploit scenario is actually feasible in the application's context
- Check if code is test-only, behind authentication, or behind a feature flag
- Web search the CWE for known false positive patterns and framework-specific mitigations
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.
- yesterday First seen · 64 lines · 59 tokens per session scan A 921d160288f7
false-positive-verifier is an agent published in the GitHub repository joaquimscosta/arkhe-claude-plugins (21 stars, last pushed yesterday), licensed MIT. It adds 59 tokens to every session and 692 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 2026-10-16.
Other agents, from other repositories
hydra-sentinel
Deep integration analysis triggered when sentinel-scan flags issues. Validates inter-component contracts, traces data flow across boundaries, confirms or dismisses findings from the fast scan, and provides specific fix suggestions. Runs on the mid tier for accuracy.
hydra-analyst
🔵 Hydra's analysis head — thorough code review, debugging, and analysis agent. Use proactively whenever Claude needs to review code for quality, analyze a bug with error messages or stack traces, evaluate dependencies, assess test coverage, review pull request changes, identify performance issues, or analyze…
hydra-guard
🟢 Hydra's security and quality gate agent. Automatically invoked after hydra-coder produces code changes. Performs a fast scan for common security issues (hardcoded secrets, SQL injection, XSS, unsafe deserialization, exposed API keys), code quality checks (unused imports, dead code, missing error handling on async…
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.
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
Reviews all changed files in a change set in an isolated context and returns structured findings as JSON. Spawned by the /review-gate:review orchestrator. Not for general questions.