What is arn-code-doctor?

An Arness workflow diagnostic agent that checks project configuration, folders, files, and skill behavior against expected patterns. Arness is the workflow system this agent is designed to inspect.

Use it when diagnosing Arness workflow issues or performing a comprehensive health check during an upgrade. It can inspect CLAUDE.md, expected directories, templates, reports, documentation, and related files.

It helps locate problems in an Arness project when a workflow behaves unexpectedly or during an upgrade. It compares the project’s setup with required directories, templates, documentation, and configuration fields.

arn-code-doctor — Agent by AppsVortex

Install

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.

agentmods

npx agentmods add agents/appsvortex/arness/arn-code-doctor

Clone the repo

git clone --depth 1 https://github.com/AppsVortex/arness

Per session 338 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,381 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

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.

Model	Per session	Once invoked
Fable 5	$0.00338	$0.01381
Opus 5	$0.00169	$0.00691
Sonnet 5	$0.00068	$0.00276
Haiku 4.5	$0.00034	$0.00138

Measured yesterday against content hash 9e41b807a668, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

arn-code-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 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.

plugins/arn-code/agents/arn-code-doctor.md · 119 lines

How it starts

The opening of the file, as written. The whole thing — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Arness Doctor

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

Input

Provided by the calling skill (arn-code-report or arn-code-init):

User's description of the issue (arn-code-report) or "comprehensive health check" instruction (arn-code-init upgrade)
Project root path
## Arness config from CLAUDE.md (if it exists)
Plugin version

Procedure

Read the Arness knowledge base at ${CLAUDE_PLUGIN_ROOT}/skills/arn-code-report/references/arness-knowledge-base.md
Based on the user's description, identify which skill(s) are involved
Run targeted checks based on the involved skill(s):
- Config checks: Read CLAUDE.md, verify ## Arness section has all required fields for the skill in question (Plans directory, Specs directory, Report templates, Template path, Template version, Template updates, Code patterns, Docs directory, Git, Platform, Issue tracker)
- Directory checks: Verify expected directories exist (plans dir, templates dir, specs dir, reports dir, docs dir)
- File checks: Verify expected files exist (template JSONs, checksums, pattern docs, phase plans, TASKS.md)
- State checks: If task-related, check task list state via conversation context
- Git checks: If git-related, run git status, check remotes
- Platform checks:
  If Platform is github:
  - Run gh auth status — verify GitHub CLI is authenticated
  - Run gh label list — verify Arness labels exist
  If Platform is bitbucket:
  - Run bkt --version — verify bkt CLI is installed
  - Run bkt auth status — verify authentication is valid
  - If Issue tracker is jira:
    - Verify Jira site and Jira project fields are populated in ## Arness config
    - Check if project's .mcp.json contains an atlassian entry (doctor cannot call MCP tools directly, but can verify config presence)
    - If Jira site or Jira project missing, report as config gap
  If Platform is none:
  - No platform-specific checks needed
  - Verify that Issue tracker is also none (consistency check)
- Comprehensive check: When invoked for a full health check (e.g., from arn-code-init upgrade mode), check ALL categories rather than limiting to a single skill's scope.
- Schema checks: Verify pattern docs comply with the schema at ${CLAUDE_PLUGIN_ROOT}/skills/arn-code-init/references/pattern-schema.md (required sections: Project Stack in code-patterns.md, Test Framework in testing-patterns.md, Technology Stack + Project Layout in architecture.md, UI Stack in ui-patterns.md if it exists).
Compare findings against expected behavior documented in the knowledge base
Produce a diagnostic report (see Output Format)

Read the full file on GitHub · 119 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.

yesterday First seen · 119 lines · 338 tokens per session scan A 9e41b807a668

Subscribe to this mod's changes

arn-code-doctor is an agent published in the GitHub repository AppsVortex/arness (33 stars, last pushed 1mo ago), licensed MIT. It adds 338 tokens to every session and 1,381 once invoked, about $0.0017 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.

Debugging Productivity Writing and docs ai-workflows claude-code claude-code-plugin developer-tools infrastructure-as-code mcp

resume

Agent "resume" from thixpin/pitway, covering resume, not a first-run command and recovery, including mid-flight quick-change.

thixpin/pitway · 28 tokens

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.

nozomi-koborinai/terradart · 0 tokens

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.

chrisallenlane/claude-swe-workflows · 42 tokens

SWE - SME GraphQL

GraphQL API design and implementation subject matter expert.

chrisallenlane/claude-swe-workflows · 16 tokens

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…

chrisallenlane/claude-swe-workflows · 79 tokens

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…

chrisallenlane/claude-swe-workflows · 93 tokens