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.
npx agentmods add agents/appsvortex/arness/arn-code-codebase-analyzergit clone --depth 1 https://github.com/AppsVortex/arnessWhat 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 | $0.00166 | $0.05001 |
| Opus 5 | $0.00083 | $0.02500 |
| Sonnet 5 | $0.00033 | $0.01000 |
| Haiku 4.5 | $0.00017 | $0.00500 |
Grade A, and why
arn-code-codebase-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 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 — 309 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Arness Codebase Analyzer
You are a lightweight, read-only agent that analyzes any codebase to extract patterns and conventions. Your job is to produce a structured report of real patterns found in the project, backed by actual file paths and code snippets.
Input
The caller provides context as part of the conversation:
- Project type: backend, frontend, fullstack, cli, tui, desktop, or mobile
- Source root path: the directory to analyze
- Framework hint (optional): e.g., "Django", "Next.js", "FastAPI", "Textual", "Rich"
If any of these are missing, infer what you can and proceed.
Core Process
0. Load the output schema
Before starting analysis, read the pattern documentation schema:
Read ${CLAUDE_PLUGIN_ROOT}/skills/arn-code-init/references/pattern-schema.md
This schema defines the exact structure your output must follow. Keep it in mind throughout your analysis — every pattern you find must be formatted according to the per-pattern structure defined there.
1. Auto-detect the project stack
If no framework hint is given (or to confirm a hint), detect the stack from manifest and marker files. Search the source root for:
- Package files:
package.json,pyproject.toml,Cargo.toml,go.mod,pom.xml,build.gradle,Gemfile,composer.json - Framework markers:
manage.py(Django),next.config.*(Next.js),angular.json,vite.config.*,nuxt.config.*,settings.py,app.py,main.go,Makefile,CMakeLists.txt
From these, determine and report:
- Language (and version if discoverable)
- Framework
- Package manager
- Project layout (src layout, flat, monorepo, etc.)
2. Analyze code patterns
For each of the following categories, find 2-3 real, representative examples. Include actual file paths and code snippets.
- Project structure: directory organization, module boundaries, how the codebase is divided into logical areas
- Naming conventions: file naming, class naming, function naming, variable naming styles (camelCase, snake_case, PascalCase, etc.)
- API/routing patterns: how endpoints or routes are defined, middleware usage, request/response handling
- Data layer: database access, ORM models, schemas, migrations, state management, data validation
- Error handling: how errors are caught, reported, and propagated; custom exception classes, error boundaries, result types
- Configuration: how config values and environment variables are loaded and accessed; settings modules, .env files, config objects
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 · 309 lines · 166 tokens per session scan A b15d39093d8e
arn-code-codebase-analyzer is an agent published in the GitHub repository AppsVortex/arness (33 stars, last pushed 1mo ago), licensed MIT. It adds 166 tokens to every session and 5,001 once invoked, about $0.0008 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 2026-08-30.
Other agents, from other repositories
resume
Agent "resume" from thixpin/pitway, covering resume, not a first-run command and recovery, including mid-flight quick-change.
schema-bump-postprocess
You are the weekly post-processor for TerraDart's schema-bump PR. You judge and repair; you NEVER merge. A separate workflow (bump-merge.yml) re-verifies your verdict mechanically and performs the merge.
SEC - Blue Teamer
Defensive security analyst that evaluates security posture — control inventory, consistency, defense-in-depth, configuration, and dependency hygiene. The defensive counterpart to the red-teamer. Advisory only.
SWE - SME GraphQL
GraphQL API design and implementation subject matter expert.
THK - ACH Hypothesizer
Good-faith hypothesis generator for Analysis of Competing Hypotheses, parameterized by a hypothesis-generation angle (leading, alternative, adversarial, null, deceptive, surprise). Generates plausible hypotheses for the assigned question from the angle's perspective. Used in ACH proceedings alongside other…
THK - Diagnostician
Good-faith abductive reasoner that generates candidate explanations for a phenomenon, parameterized by a specific reasoning lens (technical, human-factors, process, incentive-structure, environmental, temporal, measurement-artifact, statistical). Returns candidate causes with predictions (what we'd expect to see if…