arn-code

This agent should be used when the user needs to design how a specific feature should be implemented within an existing codebase, or when the arn-code-feature-spec skill needs architectural analysis of a feature proposal. <example> Context: Invoked by arn-code-feature-spec skill during iterative refinement user: "feature spec" assistant: (invokes arn-code-architect with feature idea + codebase context) </example> <example> Context: User asks how to implement a specific feature user: "how should I implement authentication in this project?" </example> <example> Context: User wants to understand integration points for a feature user: "what files would I need to change to add caching?" </example>

This agent should be used when the arn-code-batch-planning skill needs to pre-generate draft feature specifications for multiple features in parallel. Takes a single feature from any source (greenfield F-NNN, GitHub issue, Jira issue, or plain description) and produces a DRAFT_FEATURE_*.md file that feature-spec's draft detection can consume. <example> Context: Invoked by arn-code-batch-planning during parallel pre-analysis for a greenfield feature user: "batch planning" assistant: (invokes arn-code-batch-analyzer with greenfield feature F-003 context) <commentary> Batch planning spawns one batch-analyzer per selected feature in parallel. Each analyzer reads the feature file, UC documents, and codebase patterns, then writes a DRAFT_FEATURE_*.md to the specs directory. </commentary> </example> <example> Context: Invoked by arn-code-batch-planning for a GitHub issue user: "batch planning" assistant: (invokes arn-code-batch-analyzer with GitHub issue #42 reference) <commentary> For GitHub issues, the analyzer fetches the issue via gh CLI, extracts title/body/labels/comments, and produces a draft spec with moderate detail. </commentary> </example> <example> Context: Invoked by arn-code-batch-planning for a Jira issue user: "batch planning" assistant: (invokes arn-code-batch-analyzer with Jira issue PROJ-42 reference) <commentary> For Jira issues, the analyzer fetches the issue via MCP, extracts summary/description/acceptance-criteria, and produces a draft spec. </commentary> </example> <example> Context: Invoked by arn-code-batch-planning for a plain description user: "batch planning" assistant: (invokes arn-code-batch-analyzer with a text description) <commentary> For plain descriptions, the analyzer produces a basic draft with architect analysis and placeholder sections that the user will refine during exploration. </commentary> </example> This is a background agent with no user interaction — it runs autonomously and returns a structured file artifact.

This agent should be used when the arn-code-batch-merge skill needs to analyze multiple open batch PRs for cross-cutting issues before guiding the user through per-PR review. Fetches CI status, review status, mergeable status, and file changes for each PR, builds a conflict map, checks for cross-PR patterns (duplicated code, inconsistent approaches), and returns a concise structured summary. <example> Context: Invoked by arn-code-batch-merge after discovering 5 open batch PRs user: "batch merge" assistant: (invokes arn-code-batch-pr-analyzer with PR list and CHANGE_RECORD paths) <commentary> Batch merge delegates the heavy analysis to this agent to keep the main session context clean. The agent reads all PR diffs internally and returns only a distilled summary. </commentary> </example> <example> Context: Re-invoked after a PR is merged to refresh remaining PR status user: "batch merge" assistant: (re-invokes arn-code-batch-pr-analyzer with fewer PRs after one was merged) <commentary> After each merge, the agent is re-run with the remaining PRs to refresh conflict and CI status. Fewer PRs = faster analysis. </commentary> </example>

This agent should be used when a bug has been diagnosed and a fix plan exists (either inline or structured), and the fix needs to be implemented with test verification and a bug fix report. <example> Context: Invoked by arn-code-bug-spec after user approves a simple fix plan user: "fix the bug" assistant: (invokes arn-code-bug-fixer with fix plan + test instructions) </example> <example> Context: User wants to assign a bug fix task to an agent user: "assign this to the bug fixer" </example> <example> Context: Bug fix needs implementation with test coverage user: "implement the fix and make sure tests pass" </example>

This agent should be used when the user asks to "analyze codebase", "find codebase patterns", "explore project structure", "what patterns does this project use", or when invoked by the arn-code-save-plan skill to gather codebase intelligence before structuring a plan. <example> Context: User is about to save a plan and needs codebase context user: "analyze the codebase patterns for my project" </example> <example> Context: Invoked by arn-code-save-plan skill user: "save plan" assistant: (invokes arn-code-codebase-analyzer as part of the save-plan workflow) </example> <example> Context: User wants to understand codebase conventions user: "what conventions and patterns does this codebase follow?" </example>

This skill should be used when the user says "assessing", "arness assessing", "assess", "assess codebase", "technical review", "codebase assessment", "find improvements", "what should I improve", "tech debt review", "pattern compliance check", "codebase health check", "improvement plan", "review my codebase", "what needs fixing", "code quality check", "audit my code", "run an assessment", "arn-assessing", or wants a comprehensive technical assessment of the codebase against stored patterns followed by prioritized improvement execution. Chains to arn-implementing if improvements are identified.

This skill should be used when the user says "arness code assess", "arn-code-assess", "assess codebase", "technical review", "codebase assessment", "find improvements", "what should I improve", "tech debt review", "tech debt audit", "pattern compliance check", "codebase health check", "assess the project", "improvement plan", "review my codebase", "what needs fixing", "code quality check", "audit my code", "run an assessment", or wants a comprehensive technical assessment of the codebase against stored patterns followed by prioritized improvement execution through the full Arness pipeline.

This skill should be used when the user says "batch implement", "implement all", "batch execution", "implement all features", "parallel implement", "implement in parallel", "arness batch implement", "arn-code-batch-implement", "run batch implementation", "implement everything", "launch batch workers", or wants to spawn parallel worktree-isolated background agents to implement multiple pending features simultaneously. Each worker runs as a full independent session with all tools. This skill requires pending plans in .arness/plans/ — run arn-code-batch-planning first if none exist.

This skill should be used when the user says "batch merge", "merge batch", "arness batch merge", "arn-code-batch-merge", "merge all PRs", "merge batch PRs", "merge the batch", "merge implemented features", "batch merge PRs", "merge open PRs", "merge all feature PRs", "combine batch PRs", "land the batch", "land all PRs", or wants to discover open batch implementation PRs, analyze them for conflicts, determine an optimal merge order, and execute merges with user-guided conflict resolution. This skill is typically invoked after arn-code-batch-implement completes and chains to arn-code-batch-simplify upon completion.

This skill should be used when the user says "batch planning", "batch plan", "arness batch planning", "arn-code-batch-planning", "plan multiple features", "plan all features", "plan unblocked features", "plan the backlog", "plan from backlog", "batch spec and plan", "plan next features", "sequential planning", "multi-feature plan", "plan the next batch", "plan these features", "batch plan GitHub issues", "batch plan from Jira", "plan issues in batch", or wants to plan multiple features from the greenfield Feature Tracker, GitHub issues, or Jira issues in a single session. Pre-analyzes all selected features in parallel, then guides sequential spec review with pipelined plan generation. This skill is typically invoked directly or after arn-brainstorming completes and chains to arn-code-batch-implement upon completion. For single-feature planning, arn-planning is the correct entry point.