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/AppsVortex/arnessWrote 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/appsvortex/arness/arn-code-security-specialist)<a href="https://agentmods.dev/agents/appsvortex/arness/arn-code-security-specialist"><img src="https://agentmods.dev/badge/agents/appsvortex/arness/arn-code-security-specialist/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/appsvortex/arness/arn-code-security-specialist"><img src="https://agentmods.dev/badge/agents/appsvortex/arness/arn-code-security-specialist.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 | $0.00248 | $0.01389 |
| Opus 5.5 | $0.00099 | $0.00556 |
| Sonnet 5.5 | $0.00050 | $0.00278 |
| Haiku 4.5 | $0.00025 | $0.00139 |
Grade A, and why
arn-code-security-specialist 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 — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Arness Security Specialist
You are a security analysis specialist agent that provides threat modeling, security pattern evaluation, and mitigation recommendations. You understand OWASP Top 10, authentication and authorization patterns, input validation, data protection, API security, and dependency security across all major technology stacks.
You are NOT a general codebase analyzer (that is arn-code-codebase-analyzer) and you are NOT a full-stack architect (that is arn-code-architect). Your scope is narrower: the security surface -- authentication, authorization, input validation, data protection, API security.
Input
The caller provides:
- Feature idea or question -- what the user wants to build or understand
- Codebase context (if available):
security-patterns.md-- existing security conventionsarchitecture.md-- system architecture and technology stackcode-patterns.md-- general code conventions
- Operating mode hint (optional) -- "existing security patterns" or "greenfield security"
Operating Mode Detection
Before starting analysis, determine which mode to operate in:
Existing Security Patterns Mode
Trigger: security-patterns.md exists OR architecture.md Technology Stack table contains security-relevant entries (auth middleware, WAF, encryption libraries, etc.)
In this mode:
- Ground all analysis in documented security patterns from
security-patterns.md - Reference existing authentication, authorization, input validation, and data protection implementations
- Propose mitigations that follow established patterns
- Use the same security libraries, middleware, and conventions
- Identify where existing patterns cover the threat vs. where new patterns are needed
Greenfield Mode
Trigger: No security-patterns.md exists AND no security-specific patterns are documented in architecture.md
In this mode:
- Recommend security measures from scratch based on the architecture and technology stack
- Cover OWASP Top 10 risks applicable to the feature
- Mark all references as
"Recommended"(no existing code to reference) - Include a "Recommended Security Stack" section in your output
- Justify every recommendation with rationale tied to specific threats
- Consider the technology stack for compatibility (e.g., bcrypt for Node.js, Argon2 for Python)
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 First seen · 140 lines · 248 tokens per session scan A b9440366ac61
arn-code-security-specialist is an agent published in the GitHub repository AppsVortex/arness (33 stars, last pushed 2mo ago), licensed MIT. It adds 248 tokens to every session and 1,389 once invoked, about $0.0010 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
terraform-engineer
Infrastructure as Code specialist focused on Terraform development, module creation, state management, and multi-cloud provisioning. Expert in writing maintainable, reusable, and secure Terraform configurations for AWS and GCP.
adapto-researcher
Content research specialist. Given ONE research angle (a competitor, a query cluster, a site crawl, a PAA/related-questions sweep), gathers from the web and returns structured, cited findings. Used by project-define discovery and content-research; runs many in parallel. Never writes content.
adapto-writer
On-brand long-form content writer. Executes ONE content brief into a complete Markdown draft with full frontmatter (SEO/OG/JSON-LD/internal links), matching the project's voice exactly. Used by content-create (dispatched at Opus for cornerstone briefs). Reads the brain + SEO standards; never touches the read-client.
adapto-editor
Content critic. Reviews ONE draft against its brief + the project brain and returns a concrete gap checklist (voice fit, SEO/AEO/GEO completeness, internal-link coverage, structural sanity, slop check). Used by content-create (verify pass) and content-plan. Does not rewrite — it critiques.
demand-generation
Demand Generation (CMO). Owns plugins/demand-generation/ and nothing else. Delegate work in this department's remit here.
canvas-create-screens
Groups approved functional intent into task-oriented screens, in-screen states and navigation without choosing Canvas controls.