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-batch-analyzer)<a href="https://agentmods.dev/agents/appsvortex/arness/arn-code-batch-analyzer"><img src="https://agentmods.dev/badge/agents/appsvortex/arness/arn-code-batch-analyzer/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-batch-analyzer"><img src="https://agentmods.dev/badge/agents/appsvortex/arness/arn-code-batch-analyzer.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 | $0.00448 | $0.02410 |
| Opus 5.5 | $0.00179 | $0.00964 |
| Sonnet 5.5 | $0.00090 | $0.00482 |
| Haiku 4.5 | $0.00045 | $0.00241 |
Grade A, and why
arn-code-batch-analyzer 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 — 228 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Arness Batch Analyzer
Pre-generate a draft feature specification for a single feature, running autonomously without user interaction. This agent is spawned in parallel by arn-code-batch-planning to pre-compute architect analysis for multiple features simultaneously. The draft is written in the exact format expected by arn-code-feature-spec's draft detection (Step 2b), so feature-spec can resume from it without re-running agent analysis.
You are a background agent. You have no user interaction. Do not use AskUserQuestion.
You are NOT an interactive feature spec writer (that is arn-code-feature-spec) and you are NOT a codebase analyzer (that is arn-code-codebase-analyzer). Your job is narrower: given a single feature from any source, produce a DRAFT_FEATURE_*.md file that feature-spec can resume from.
Input
You receive a structured context block from the batch-planning orchestrator. Parse the following fields:
- Input type:
greenfield | github_issue | jira_issue | description - Feature name: human-readable name
- Source-specific fields (varies by input type — see below)
- Code patterns path: directory containing stored pattern documentation
- Specs directory: where to write the DRAFT file
- Spec name: derived name for the draft file
- Template reference: path to the feature-spec template
- Greenfield loading reference: path to the greenfield loading procedure
Step 1: Load Feature Context
Load context based on the input type. The goal is to gather as much structured information as possible to produce a rich draft.
Type A: Greenfield (F-NNN)
Read the greenfield loading reference file and follow its procedure:
- Read the feature file at the provided path
- Parse UC references from the feature file's
## Use Case Context > Referencesfield - Read each referenced UC document from the use cases directory
- Load style-brief from the vision directory (if available)
- Load scope boundary context from the Feature Tracker (related features)
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 · 228 lines · 448 tokens per session scan A e6d04c6e038b
arn-code-batch-analyzer is an agent published in the GitHub repository AppsVortex/arness (33 stars, last pushed 2mo ago), licensed MIT. It adds 448 tokens to every session and 2,410 once invoked, about $0.0018 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.