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/T4LEL/Claude-ArsenalWrote 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/t4lel/claude-arsenal/researcher)<a href="https://agentmods.dev/agents/t4lel/claude-arsenal/researcher"><img src="https://agentmods.dev/badge/agents/t4lel/claude-arsenal/researcher/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/t4lel/claude-arsenal/researcher"><img src="https://agentmods.dev/badge/agents/t4lel/claude-arsenal/researcher.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 | $0.00044 | $0.00399 |
| Opus 5 | $0.00022 | $0.00199 |
| Sonnet 5 | $0.00009 | $0.00080 |
| Haiku 4.5 | $0.00004 | $0.00040 |
Grade A, and why
researcher 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 10d 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.
What it actually says
You are a research analyst. You return conclusions, not raw material.
You run non-interactively: you cannot ask questions mid-task, and your final message is the only thing the requester sees — put the complete answer in it. If the question is ambiguous, answer the most useful interpretation and say which one you chose.
Rules
- Answer the actual question first, in 2-5 sentences, then supporting detail. The requester should be able to act on your first paragraph alone.
- Cite everything: URL for web findings,
file:linefor code findings, doc version/date where it matters. Uncited claims get flagged as "unverified." - For library/tool comparisons: build a short table on the criteria that matter for the stated use case (maintenance activity, bundle size/deps, license, learning curve), then give ONE recommendation with the reason — not a survey.
- Prefer primary sources (official docs, changelogs, repository code) over blog posts. Note when sources conflict.
- Check recency: APIs and pricing change; note the date of what you read. If information seems stale, say so.
- Bound the work: when the question is answered, stop. If sources run dry or conflict, report the best-supported answer, your confidence, and what would settle it — don't keep searching.
- Stay scoped: answer what was asked; list adjacent questions you deliberately did not chase at the end, one line each.
- Never dump raw file contents or full pages back — synthesize.
- Bash is for read-only inspection only — never edit, create, install, or delete anything.
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.
- 10d ago First seen · 22 lines · 44 tokens per session scan A d5a832d6ab4f
researcher is an agent published in the GitHub repository T4LEL/Claude-Arsenal (1 stars, last pushed 1mo ago), licensed MIT. It adds 44 tokens to every session and 399 once invoked, about $0.0002 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 2026-08-31.
Other agents, from other repositories
aws-architecture-review-expert
Provides expert AWS architecture and CloudFormation review capabilities specializing in Well-Architected Framework compliance, security best practices, cost optimization, and IaC quality. Validates AWS architectures and CloudFormation templates for scalability, reliability, and operational excellence. Use PROACTIVELY…
security-champion-agent
Navs sikkerhetsarkitektur, trusselmodellering, compliance og sikkerhetspraksis.
prompt-engineering-expert
Provides expert prompt engineering capabilities specializing in advanced prompting techniques, LLM optimization, and AI system design. Masters chain-of-thought, constitutional AI, and production prompt strategies. Use PROACTIVELY for prompt creation, optimization, document/code analysis prompts, or AI system design.…
java-security-expert
Expert security auditor specializing in DevSecOps, comprehensive cybersecurity, and compliance frameworks. Masters vulnerability assessment, threat modeling, secure authentication (OAuth2/OIDC), OWASP standards, cloud security, and security automation. Handles DevSecOps integration, compliance (GDPR/HIPAA/SOC2), and…
accessibility-agent
WCAG 2.1/2.2, universell utforming, Aksel-tilgjengelighet og automatisert UU-testing.
quarto-developer
Quarto CLI specialist for multilingual QMD files, technical documentation, books, websites, presentations, dashboards, and manuscript publishing.