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 skills/appsvortex/arness/arn-code-helpnpx skills add AppsVortex/arness --skill arn-code-helpgit 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 | $0.00078 | $0.02487 |
| Opus 5 | $0.00039 | $0.01243 |
| Sonnet 5 | $0.00016 | $0.00497 |
| Haiku 4.5 | $0.00008 | $0.00249 |
Grade A, and why
arn-code-help 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 — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Arness Help
Detect the user's current position in the Arness workflow pipeline, render an ASCII diagram with the active stage marked, and suggest the next command to run. Supports cross-plugin awareness — detects activity in Arness Spark and Arness Infra and provides hints at the bottom of the output. This skill is strictly read-only -- it never modifies files or project state.
Allowed tools: Read, Glob, Grep only. This skill MUST NOT use Write, Edit, Bash, or Task tools. This skill MUST NOT invoke any agents.
Workflow
Step 0: Multi-Plugin Awareness
- From the
## Arnesssection (loaded in Step 1), detect other plugin field groups:- spark_fields_present: true if
Vision directoryORUse cases directoryORPrototypes directorypresent - infra_fields_present: true if
Infra plans directoryORInfra specs directorypresent
- spark_fields_present: true if
- For each detected plugin, do a quick existence check (max 2 files):
- Spark: Check if
<Vision directory>/product-concept.mdexists - Infra: Check if
<Infra plans directory>has any subdirectories, OR ifDockerfileordocker-compose.ymlexists in the project root
- Spark: Check if
- Record
{ plugin_name, has_activity: bool }for each detected plugin. - Proceed to Step 1. Cross-plugin hints are appended AFTER own status is rendered in Step 3.
Step 1: Load Configuration
- Read the project's
CLAUDE.mdfile. - Extract the
## Arnesssection. - From the
## Arnesssection, extract core fields:- Plans directory (e.g.,
.arness/plans/) - Specs directory (e.g.,
.arness/specs/) - Docs directory (e.g.,
.arness/docs/)
- Plans directory (e.g.,
If ## Arness is missing: Skip to Step 3 and render the core pipeline diagram with all stages unmarked. Suggest the user run /arn-planning to get started for an existing project, or /arn-brainstorming for a brand-new project (requires arn-spark). Do not attempt detection.
Step 2: Detect Pipeline Position
Read the pipeline reference file at ${CLAUDE_PLUGIN_ROOT}/skills/arn-code-help/references/pipeline-map.md to load detection rules, context-aware rendering rules, and next-step tables.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 141 lines · 78 tokens per session scan A 7411f8527ff3
arn-code-help is a skill published in the GitHub repository AppsVortex/arness (33 stars, last pushed 1mo ago), licensed MIT. It adds 78 tokens to every session and 2,487 once invoked, about $0.0004 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 skills, from other repositories
agent-framework-azure-ai-py
Build persistent agents on Azure AI Foundry using the Microsoft Agent Framework Python SDK.
agentmail
Email infrastructure for AI agents. Create accounts, send/receive emails, manage webhooks, and check karma balance via the AgentMail API.
aria
Designs the data model, API contracts, and structural foundation of the system.
luna
Reviews code for objective correctness, security, and reliability.
max
Cleans up and improves existing code without changing behavior.
agent-self-scheduling
Schedule AI agent runs with cron, loops, or external clocks while avoiding unsafe tight autonomous timers.