Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add AppsVortex/arness/plugin install arn-sparkWrote 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/skills/appsvortex/arness/arn-spark-init)<a href="https://agentmods.dev/skills/appsvortex/arness/arn-spark-init"><img src="https://agentmods.dev/badge/skills/appsvortex/arness/arn-spark-init/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/skills/appsvortex/arness/arn-spark-init"><img src="https://agentmods.dev/badge/skills/appsvortex/arness/arn-spark-init.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 | $0.00177 | $0.04691 |
| Opus 5.5 | $0.00071 | $0.01876 |
| Sonnet 5.5 | $0.00035 | $0.00938 |
| Haiku 4.5 | $0.00018 | $0.00469 |
Grade A, and why
arn-spark-init 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 today.
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 — 313 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Arness Spark Init
Set up Arness for a greenfield project by configuring output directories for all greenfield artifacts and detecting the project's platform setup. This is optional — Arness Spark auto-configures with sensible defaults on first skill invocation. Use this to customize directories, add design tool integrations (Figma, Canva), or review your current settings.
This skill is lightweight and focused: it configures only what greenfield skills need (artifact directories and platform integration). It does NOT set up code patterns, report templates, plans, or documentation directories — those are handled when the project transitions to the development phase. Design tool integration (Figma/Canva) is only available through this skill — ensure-config does not configure design tools.
The ## Arness section written by this skill is forward-compatible with Arness Code and Arness Infra. When either plugin's ensure-config or init runs later, it detects the existing configuration and adds the remaining fields without disrupting greenfield settings.
Workflow
Step 1: Check Existing Configuration
Read the project's CLAUDE.md and look for a ## Arness section. If no CLAUDE.md exists, create one at the project root before proceeding.
If the section does not exist:
- Proceed to Step 2 (fresh init)
If the section exists:
- Parse all config fields from the existing
## Arnessblock - Read the current plugin version from
${CLAUDE_PLUGIN_ROOT}/.claude-plugin/plugin.json - Show the user their current configuration
- Ask via
AskUserQuestion:- Review — Show current configuration summary, no changes
- Update — Check for missing greenfield fields and fill them in
- Reconfigure — Re-run the full setup flow from scratch
- Keep — No changes
- If Review → display a clean summary of all
## Arnessfields relevant to Arness Spark, then exit the skill - If Keep → done, exit the skill
- If Reconfigure → continue to Step 2, pre-filling known values as defaults
- If Update → check which greenfield fields are missing (Vision directory, Use cases directory, Prototypes directory, Spikes directory, Visual grounding directory, Reports directory, Git, Platform, Issue tracker, Figma, Canva) and only process those. For missing directory fields, ask the user with the existing value as the default. For missing Git/Platform/Issue tracker, re-run Step 3 detection. For missing Figma/Canva, re-run Step 3.4 design tool integration. Then proceed to Step 4 to write the updated config. Preserve all existing fields that are not managed by this skill (such as Plans directory, Specs directory, Report templates, etc.).
What ships with it
5 files 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.
- today First seen · 313 lines · 177 tokens per session scan A 9dc311bdb363
arn-spark-init is a skill published in the GitHub repository AppsVortex/arness (33 stars, last pushed today), licensed MIT. It adds 177 tokens to every session and 4,691 once invoked, about $0.0007 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 2026-10-25.
Other skills, from other repositories
contribution-workflow
Design or document how new work enters a design system: contribution types, proposal criteria, review stages, sign-off and release. Triggers: contribution process, how should someone contribute, contribution guidelines, adding a new component. Not for audit findings to tickets (backlog-generator).
designer-coordination-rules
COORDINATION RULES — extracted from roles.json deepPrompt for designer.
silver-ingest
This skill should be used for external artifact ingestion: JIRA/Figma/Google Docs to SPEC.md + DESIGN.md via MCP connectors, plus cross-repo spec fetch with version pinning.
sb:ingest
This skill should be used for external artifact ingestion: JIRA/Figma/Google Docs to SPEC.md + DESIGN.md via MCP connectors, plus cross-repo spec fetch with version pinning.
interface-craft
Raises the visual and interaction quality of an interface — layout, hierarchy, type, spacing, density, and the details that separate a considered product from a generic one. Use this when a screen works but looks unfinished or default, when a layout feels crowded or arbitrary, when a page has no clear focal point, or…
vendor-management
Selects, contracts, and manages suppliers and vendors — requirements, evaluation, negotiation support, onboarding, performance management, and exit. Use this to choose a vendor, run a selection process, structure a service agreement's operational terms, manage an underperforming supplier, plan an exit or migration, or…