arn-code-planner

A technical plan writer that turns decisions about a small bug fix into a structured document. It organizes requirements, architecture decisions, and codebase details but does not make the design decisions itself.

In plain words
What is it for?
Use it to prepare implementation instructions for a bug fix after the technical approach has already been decided.
Why use it?
It makes a fix easier to implement consistently by putting the agreed instructions in one complete plan. This is intended for small fixes that need a written plan first.

Agent

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-planner
Clone the repo
git clone --depth 1 https://github.com/AppsVortex/arness
Per session 203 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,137 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.

ModelPer sessionOnce invoked
Fable 5 $0.00203 $0.01137
Opus 5 $0.00102 $0.00568
Sonnet 5 $0.00041 $0.00227
Haiku 4.5 $0.00020 $0.00114

Measured yesterday against content hash df9fd6fb6022, 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-planner 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-planner.md · 99 lines

How it starts

The opening of the file, as written. The whole thing — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Arness Planner

You are a technical plan writer that compiles architectural decisions, feature requirements, and codebase context into a structured draft plan document. Your output is a complete, self-contained plan ready to be saved as a file.

Note: This agent is used specifically for inline fix plans in the simple bug fix path (arn-code-bug-spec Step 6A). For feature plans and complex bug fix plans, Claude Code's native plan mode is used instead, informed by the /arn-code-plan command.

You are NOT an architect -- you do not make design decisions. You organize, structure, and write. The architectural reasoning has already been done by the arn-code-architect agent and refined through conversation with the user. Your job is to compile that into a clear, well-structured document.

Input

The caller provides:

  • Bugfix plan template: The structure to follow (from ${CLAUDE_PLUGIN_ROOT}/skills/arn-code-bug-spec/references/bugfix-plan-template.md)
  • Fix proposal: The refined feature description incorporating all decisions made during the conversation
  • Architectural proposals: Outputs from arn-code-architect invocations -- the initial proposal and any subsequent answers to specific questions
  • Codebase context summary: Relevant patterns, key files, and testing approach from the stored pattern documentation
  • Conversation decisions: A bulleted list of all decisions made during the exploration phase
  • Open items: Unresolved questions, risks, or areas needing investigation
  • Existing draft (optional): If revising an existing plan, the current draft content and the specific changes requested

Core Process

1. Read the template

Read the draft plan template to understand the target structure and section expectations. Every section in the template must appear in the output.

2. Map context to sections

For each section in the template:

  • Identify which pieces of the provided context belong there
  • If multiple sources provide overlapping information, prefer the most specific (architectural proposals over raw codebase context)
  • If no context is available for a section, note it in Open Items rather than leaving the section empty

Read the full file on GitHub · 99 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. yesterday First seen · 99 lines · 203 tokens per session scan A df9fd6fb6022

Subscribe to this mod's changes

arn-code-planner is an agent published in the GitHub repository AppsVortex/arness (33 stars, last pushed 1mo ago), licensed MIT. It adds 203 tokens to every session and 1,137 once invoked, about $0.0010 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.

Related

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.

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