arn-spark-doctor

arn-spark-doctor is an agent for Claude Code from AppsVortex/arness. It costs 212 tokens per session (980 once invoked), scanned A, original, MIT.

A diagnostic agent for Arness Spark workflow problems. It compares project configuration, folders, files, and skill behaviour with the expected Spark setup and reports Spark-specific issues.

In plain words
What is it for?
Use it to investigate problems in Spark workflows, check required directories and files, and identify configuration mismatches.
Why use it?
It helps locate missing configuration or workflow artifacts without mixing in unrelated project problems.

Agent for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable. Also seen: model in frontmatter; mentions .claude-plugin; mentions CLAUDE.md.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the arn-spark plugin — 28 skills, 20 agents shipped together

Good fit Use it to investigate problems in Spark workflows, check required directories and files, and identify configuration mismatches.

Compare 6 agents from other repositories ↓
Install

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.

Claude Code
/plugin marketplace add AppsVortex/arness
Claude Code
/plugin install arn-spark

Made for: Claude Code.

Or install arn-spark, the plugin that ships this one along with the rest of its 28 skills, 20 agents.

Wrote 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.

agentmods badge for arn-spark-doctor

README.md
[![agentmods](https://agentmods.dev/badge/agents/appsvortex/arness/arn-spark-doctor/github.svg)](https://agentmods.dev/agents/appsvortex/arness/arn-spark-doctor)
Your own site
<a href="https://agentmods.dev/agents/appsvortex/arness/arn-spark-doctor"><img src="https://agentmods.dev/badge/agents/appsvortex/arness/arn-spark-doctor/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.

agentmods 80×15 button for arn-spark-doctor

Your own site · 80×15
<a href="https://agentmods.dev/agents/appsvortex/arness/arn-spark-doctor"><img src="https://agentmods.dev/badge/agents/appsvortex/arness/arn-spark-doctor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 212 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 980 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00212 $0.00980
Opus 5.5 $0.00085 $0.00392
Sonnet 5.5 $0.00042 $0.00196
Haiku 4.5 $0.00021 $0.00098

Measured today against content hash 74aac2022dba, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

arn-spark-doctor 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.

plugins/arn-spark/agents/arn-spark-doctor.md · 93 lines

How it starts

The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Arness Spark Doctor

Arness Spark workflow diagnostic specialist. Analyzes a project's Arness Spark state against expected patterns to identify greenfield workflow issues.

Input

Provided by the calling skill (arn-spark-report):

  • User's description of the issue
  • Project root path
  • ## Arness config from CLAUDE.md (if it exists)
  • Plugin version

Procedure

  1. Read the Spark knowledge base at ${CLAUDE_PLUGIN_ROOT}/skills/arn-spark-report/references/spark-knowledge-base.md
  2. Based on the user's description, identify which skill(s) are involved
  3. Run targeted checks based on the involved skill(s):
    • Config checks: Read CLAUDE.md, verify ## Arness section has the required Spark fields (Vision directory, Use cases directory, Prototypes directory, Spikes directory, Visual grounding directory, Reports directory)
    • Directory checks: Verify expected directories exist (vision dir, use cases dir, prototypes dir, spikes dir, visual grounding dir, reports dir)
    • File checks: Verify expected artifact files exist based on which pipeline stage the issue is at (product-concept.md, architecture-vision.md, naming-brief.md, stress test reports, UC-*.md files, LOCKED.md, feature-backlog.md)
    • Platform checks: Run gh auth status if the issue involves feature upload or issue tracker integration
    • Node/Playwright checks: If the issue involves scaffold, prototype, or visual skills, run node --version, npm --version, npx playwright --version
    • Git checks: If relevant, run git status, git remote -v
  4. Compare findings against expected behavior documented in the knowledge base
  5. Produce a diagnostic report (see Output Format)

Output Format

## Diagnostic Report

**Skill(s) involved:** [skill names]
**Plugin version:** [from plugin.json]
**Config state:** [relevant ## Arness Spark fields, or "not configured"]

### Findings

1. [ISSUE] <specific finding> — Expected: <what should happen>. Actual: <what was observed>.
2. [OK] <check that passed>
...

### Assessment

<1-3 sentence summary of the root cause or likely explanation>

### Suggested Resolution

<What the user or maintainer should do to fix this>

Read the full file on GitHub · 93 lines

Changes

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.

  1. today First seen · 93 lines · 212 tokens per session scan A 74aac2022dba

Subscribe to this mod's changes

arn-spark-doctor is an agent published in the GitHub repository AppsVortex/arness (33 stars, last pushed today), licensed MIT. It adds 212 tokens to every session and 980 once invoked, about $0.0008 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.

Related

Other agents, from other repositories

quality-fixer

Specialized agent for verifying software projects and fixing quality failures within the current task scope. Use proactively after code changes or for quality, test, build, lint, format, correctness, or fix requests.

shinpr/claude-code-workflows · 44 tokens

doctrine-performance-optimizer

Read-only performance audit of Doctrine usage: N+1 queries, fetch modes, batch processing, missing indexes, and caching opportunities. Use proactively after adding entities, relations, repository queries, or when a page/endpoint is reported slow.

dev-toolings/superpowers-symfony · 53 tokens

debugger

Root-cause debugging: reproduce, confirm the cause with evidence, apply a minimal fix and prove it with a regression test. Use for bugs, flaky tests or errors of unknown cause.

KevinZai/commander · 40 tokens

evolve-telemetry-coverage-check

Observability completeness gate for the Evolve Loop (Evaluate archetype). The advisor INSERTS this phase after Build on cycles whose scout.goaltype == "observability" to verify every newly added code path is debuggable in production before ship.

mickeyyaya/evolve-loop · 58 tokens

architect

Deep technical work. Use for complex implementation, deep debugging, cross-module reasoning, architecture review, and risky or security-sensitive changes (auth, billing, migrations, concurrency, caching, data consistency, public APIs). Also reviews work from cheaper agents for hidden flaws.

realgarit/fable-baton · 54 tokens

code-explorer

Read-only codebase explorer — searches, maps, and explains code structure. Use when a skill needs to delegate codebase exploration without risk of modification.

harnessprotocol/harness-kit · 34 tokens