Skip to content

Dev Plugin

Accelerate development with seven specialist agents, nineteen skills, multi-agent team orchestration, and behavioral skill nudges that watch your work across every installed plugin. The dev plugin is the most-used Agronod plugin — most other plugins compose against its agents and skills.

Source: agronod/claude-plugins → plugins/dev

At a Glance

  • 7 specialist agents — architect, engineer, researcher, critic, code-writer, experience-analyst, storyteller
  • 19 skills — 6 you invoke directly, 13 that agents load for process and discipline
  • Team orchestration — assemble multi-agent teams with leadership protocols and a live dashboard
  • Skill awareness — watches your tool usage across all installed plugins and suggests skills when patterns emerge
  • 5 hooks — auto-approve reads, detect LSP tools, inject linting config, behavioral skill nudges, cross-plugin skill index

Install

bash
/plugin marketplace add agronod/claude-plugins
/plugin install dev@agronod-plugins
/dev:setup

/dev:setup validates your environment and installs the claude-server binary required by team skills.

Daily Surface Area

The skills you invoke directly:

bash
/dev:research          # Research a library, API, or tech decision
/dev:review            # Review changed code for quality and patterns
/dev:spawn-team        # Ad-hoc team for analysis or deliberation
/dev:team-feature      # Plan-then-implement a feature with a team
/dev:team-dashboard    # Watch agent teams work in real time
/dev:setup             # Validate plugin environment

Agents and Skills

Agents define who does the work. Skills define how it gets done. Any agent can load any skill — they compose freely.

Agents

AgentSeesContributes
architectSystem boundaries, data models, contractsIntegration strategy, design trade-offs
engineerTech stack, conventions, core logic, testingImplementation patterns, validation
code-writerFocused implementation scopeDetailed, clean code from a blueprint
researcherWeb, docs, source codeAnswers, options, evidence
experience-analystUser flows, error states, edge casesUX and accessibility concerns
criticFailure modes, assumptions, pre-mortemsRisk analysis, adversarial review
storytellerDecision context, narrative flowADRs, changelogs, design docs, post-mortems

Invocable Skills

The six skills you invoke directly cover the most common workflows:

/dev:research — Assembles current docs and code examples for a library, API, or architecture question. Start here when the documentation is stale or you need to verify behavior across versions.

/dev:review — Reviews changed code for quality, patterns, and maintainability. Load this before committing multi-file changes or opening a PR.

/dev:spawn-team — Assembles agents with different expertise (architect, researcher, critic) to explore a question or decision from multiple angles. Use when the right approach isn't obvious and benefits from debate.

/dev:team-feature — Orchestrates a full team for features spanning 3+ files: a leader that plans, parallel implementers, and a critic that spots risks. Both planning and implementation happen together with live status.

/dev:team-dashboard — Displays real-time status of running teams in a browser window. Pair this with /dev:team-feature or /dev:spawn-team to watch progress and debug blockages as they happen.

/dev:setup — Validates your environment and installs the claude-server binary required by team skills. Run this once after install or if team skills fail to start.

Agent-Loaded Skills

These don't surface as slash commands — agents load them when their work calls for the protocol.

SkillEnforces
codeProduction quality: no TODOs, clarity, completeness
explorePre-implementation investigation: trace data flow, map contracts
test-writingIntegration-first tests, mock externals only
readmeREADME quality standards: progressive disclosure, format selection
technical-writingAudience identification, progressive disclosure, editorial standards
prompt-writingCalibrated system prompts that don't over-prescribe
team-leaderDelegation, synthesis, decision-making
team-memberReporting, disagreement, collaboration
propose-skillWorkflow-gap detection and skill proposals
skill-description-writerTrigger optimization for autonomous activation
skill-healthTriage for skill-ecosystem problems (gap, drift, overlap, trigger-blindness)
update-skillBody updates when documented workflow drifts from actual behavior
reconcile-skillsOverlap resolution — merge, differentiate, or absorb

Team Orchestration

/dev:team-feature assembles a team that plans collectively, implements in parallel, and reports through a live dashboard:

/dev:spawn-team is the lighter sibling — ad-hoc teams for analysis, debate, or research without the plan-then-implement structure. Both require the CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1 environment variable that /dev:setup sets up.

Deciding Between Single Agent and Team

For focused work — a bug fix, small refactor, or feature in one or two files — a single agent or no agent is faster and cheaper. Use /dev:spawn-team when a decision or analysis would benefit from multiple expert perspectives: architect reviewing boundaries, researcher exploring unfamiliar tech, critic stress-testing assumptions. Features spanning 3+ files where both planning and implementation matter should go through /dev:team-feature, which ensures the plan is sound before agents write code in parallel. Each agent in a team can ask others for clarification or critique; spawning multiple isolated agents and reconciling results yourself loses that collaboration.

Hooks

Five hooks run automatically:

HookEventWhat it does
Auto-approvePreToolUseSkips confirmation for read-only operations (git status, GitHub queries, docs lookups). Writes still confirm.
Linting injectionPreToolUse (matcher: Task)Loads project lint config into spawned subagents so they respect your rules.
LSP detectionSessionStartDetects LSP tool providers and injects guidance for using them over Grep/Glob.
Skill indexSessionStartIndexes skills across all installed plugins, not just dev.
Skill awarenessPostToolUse + UserPromptSubmitWatches tool patterns and nudges when a skill would help.

The skill awareness system fires across plugins. It runs the same logic for dev:code, meta:challenge, or any third-party plugin's skills — once installed, they're all candidates for nudging.

The system watches patterns in your tool use and suggests a skill when a pattern emerges. Here are the patterns it recognizes:

PatternThresholdSuggests
Source file edits without a coding skill3+ editsCoding discipline
Grep/Glob searches without exploration5+ searchesSystematic investigation
WebFetch/WebSearch without research2+ callsResearch protocol
Test file edits without testing skill2+ editsIntegration testing
Edits across many files4+ filesFeature orchestration
Reading many source files5+ filesCode review

You receive a maximum of 3 nudges per session — one per category — and the system stays silent if a relevant skill is already loaded.

Auto-Approve Matrix

Operations that skip confirmation
CategoryAuto-approvedScope
Gitstatus, log, diff, branch, show, rev-parse, remote, describe, tag, merge-base, ls-files, ls-treeCurrent repo only
GitHub CLIpr list/view/status/checks/diff, issue list/view/status, repo view/listCurrent repo or Agronod org
GitHub MCPget_*, list_*, search_*, pull_request_read, issue_readAgronod org only
Documentation MCPAll lookupsNone
IDE MCPgetDiagnostics, getOpenFiles, getActiveFileNone
HTTPcurl GET onlyNo upload flags
Built-inWebSearch, ListMcpResourcesTool, ReadMcpResourceToolNone
Skills & SubagentsAll invocationsNone

Never auto-approved: git push/commit/reset, file edits, GitHub ops on non-Agronod repos, POST/PUT/DELETE requests.

Cross-Plugin Composition

Dev's agents are reusable across all plugins. The specs plugin chains dev:researcher during planning and dev:code-writer during build; any skill can spawn dev:critic for review or dev:storyteller for documentation. Reference agents by their qualified name: subagent_type: "dev:engineer".

Built with VitePress and powered by Claude Code