By Conava
Full development lifecycle pipeline: brainstorm, plan, implement (parallel TDD), review, debug, document — with strict security hooks for bypass mode
Use this agent for bugs, test failures, or unexpected behavior. Follows scientific debugging: reproduce, gather evidence, hypothesize, test, fix, verify. <example> Context: Tests failing user: "The auth tests are failing with a null pointer exception" assistant: "I'll use the debugger agent to investigate the null pointer exception." </example>
Final quality gate. Comprehensive review covering security, credentials, code quality, tech debt, conventions, plan compliance, and architecture. Runs on any completed implementation. <example> Context: All tasks implemented and reviewed user: "Everything is reviewed, do the final deep review" assistant: "I'll use the deep-review agent for the final quality review." </example>
Use this agent for complex dependency migrations that involve breaking changes, API refactoring, package renames, or behavioral differences. Unlike the dependency-patcher (simple version bumps), this agent researches migration guides, runs ecosystem migration tools (OpenRewrite, Rector, codemods), refactors application code, and ensures everything compiles and passes tests. Launched by the migrate skill — never invoked directly. <example> Context: Migrate skill dispatching a Spring Boot 2→3 migration user: "Migrate spring-boot from 2.7.18 to 3.2.x in /home/user/repos/my-api. Migration guide: [URL]. Known changes: javax→jakarta namespace, Spring Security config changes." assistant: "I'll use the dependency-migrator agent to execute the Spring Boot 3 migration with OpenRewrite recipes and manual code fixes." <commentary> Complex migration with namespace changes, config changes, and potential behavioral differences. Needs Opus-level reasoning. </commentary> </example> <example> Context: Migrate skill dispatching AWS SDK v1→v2 user: "Migrate aws-sdk-java from 1.x to 2.x in /home/user/repos/billing-service. Use the AWS SDK migration tool (OpenRewrite recipe)." assistant: "I'll use the dependency-migrator agent to run the AWS SDK migration tool and handle remaining manual changes." <commentary> Migration with dedicated tooling available. Agent runs the tool first, then handles what it can't automate. </commentary> </example>
Use this agent to patch dependencies in a single repository. It detects ecosystems, checks if dependencies are affected, updates versions, verifies the build/tests pass, and commits+pushes. Launched by cve-patcher, eol-fixer, or other dependency management skills — never invoked directly by the user. <example> Context: CVE patcher launching per-repo agents user: "Patch CVE-2024-38816 (spring-webmvc, Maven, fix: 6.1.13) in /home/user/repos/my-api" assistant: "I'll use the dependency-patcher agent to check and patch the Spring vulnerability in my-api." <commentary> CVE patcher researched the CVE and is now dispatching a patcher agent to handle one repo. </commentary> </example> <example> Context: EOL fixer launching per-repo agents user: "Update express from 4.18.2 to 4.19.0 (CVE-2024-XXXXX) in /home/user/repos/frontend-app" assistant: "I'll use the dependency-patcher agent to update express in frontend-app." <commentary> CVE patcher dispatching a simple version bump to a second repo in parallel. </commentary> </example>
Use this agent for build systems, CI/CD, Docker/containers, infrastructure as code, dev tooling, package management, or deployment. <example> Context: CI/CD work user: "Set up GitHub Actions for the new service" assistant: "I'll use the devops agent to configure the CI/CD pipeline." </example>
This skill should be used when the user asks to "brainstorm", "refine an idea", "flesh out a feature", "define requirements". Guides interactive refinement of rough ideas into concise, actionable feature specifications. Focuses on the "what" and architecture — never the "how".
Brand voice, visual identity, messaging frameworks, asset management, brand consistency. Activate for "brand", "brand identity", "voice", "visual identity", "brand guidelines", "messaging framework", "brand consistency", branded content, tone of voice, marketing assets, brand compliance, style guides.
Patch CVE vulnerabilities across one or many repositories. Invoke with a list of CVEs and optionally specific repo names. Researches each CVE (affected package, ecosystem, versions), then launches dependency-patcher agents to update, verify, commit, and push. Use this skill whenever the user mentions CVEs, security vulnerabilities in dependencies, patching dependencies, or updating packages for security fixes — even if they don't say 'CVE' explicitly but reference a security advisory or vulnerable dependency.
This skill should be used when the user asks to "debug this", "fix this bug", "find the root cause", "investigate an error", "troubleshoot", "why is this failing", "trace the issue", or mentions errors, exceptions, stack traces, or unexpected behavior that needs investigation. Launches the debugger agent for systematic root cause analysis.
Final comprehensive pull request review — the last gate before merge. Checks security, credentials, code quality, tech debt, conventions, and plan compliance.
Executes bash commands
Hook triggers when Bash tool is used
Modifies files
Hook triggers on file write and edit operations
Uses power tools
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Uses Bash, Write, or Edit tools
Uses Bash, Write, or Edit tools
A Claude Code plugin that turns a rough idea into merge-ready code. It brainstorms scope, plans a TDD architecture, implements tasks in parallel worktrees, reviews every line, updates your docs, and runs a final security audit. You approve twice (after brainstorm, after plan) and get working code back.
%%{init: {'theme': 'neutral'}}%%
flowchart TD
input["Your idea"] --> brainstorm
subgraph interactive["Interactive — you decide"]
brainstorm["Brainstorm\nClarifying questions, feature spec"]
design["Design System\n67 styles, 161 palettes, 57 fonts"]
plan["Plan\nTDD architecture, parallel tasks"]
brainstorm --> design
design -. "only if UI" .-> plan
brainstorm --> plan
end
plan --> approve{You approve}
approve --> impl
subgraph impl["Parallel Implementation"]
direction LR
a1["Agent 1\nWorktree A"] --> r1["Review"]
a2["Agent 2\nWorktree B"] --> r2["Review"]
a3["Agent 3\nWorktree C"] --> r3["Review"]
end
impl --> docs["Documentation\nREADME, API docs"]
docs --> deep["Deep Review\nSecurity audit, regression check, e2e trace"]
deep --> done["Done\nCommit, merge, or iterate"]
classDef interactive_node fill:#dbeafe,stroke:#2563eb,color:#1e3a5f
classDef approve_node fill:#fef3c7,stroke:#d97706,color:#78350f
classDef impl_node fill:#d1fae5,stroke:#059669,color:#064e3b
classDef review_node fill:#fce7f3,stroke:#db2777,color:#831843
classDef final_node fill:#f3f4f6,stroke:#6b7280,color:#1f2937
class brainstorm,design,plan interactive_node
class approve approve_node
class a1,a2,a3 impl_node
class r1,r2,r3 review_node
class docs,deep,done final_node
Every finding from every review gets fixed. There's no "pass with warnings." If an implementer can't fix it after two attempts, the planner rewrites the approach.
claude plugin add devline
git clone https://github.com/devline-io/claude-devline.git
claude --plugin-dir ./claude-devline
Then run /devline:setup in your project. It creates a CLAUDE.md (project context for agents) and a .claude/devline.local.md (pipeline settings) through an interactive walkthrough.
jq, git, ghexport CLAUDE_CODE_MAX_OUTPUT_TOKENS=128000 in your shell profile. The frontend designer and other agents produce large outputs (HTML previews, design systems). The default 32K limit will cut them off.Devline is built for --dangerously-skip-permissions mode. Agents need to read files, write code, and run builds without prompting on every tool call.
Safety comes from hooks, not permission dialogs. The plugin ships 85+ security rules that block destructive operations before they execute. Force pushes, rm -rf outside the working dir, credential exposure, publishing commands, database destructive operations -- all blocked. See Security Hooks.
claude --dangerously-skip-permissions
It works without bypass mode too. You'll just get prompted frequently during parallel implementation.
| Command | What it does |
|---|---|
/devline <idea> | Full pipeline -- brainstorm through deep review |
/devline:brainstorm <idea> | Refine an idea into a feature spec |
/devline:plan <spec> | Create a TDD implementation plan |
/devline:implement | Implement tasks from an existing plan |
/devline:review | Code review of recent changes |
/devline:debug <error> | Systematic root cause analysis |
/devline:deep-review | Final merge-readiness audit |
/devline:cve-patcher <CVEs> | Patch vulnerabilities across repos |
/devline:migrate <package> | Major version migrations with breaking changes |
/devline:design | Standalone component or theme design |
/writing | Write, edit, or translate text — anti-AI-pattern rewriting for general text; citation contract enforcement for scientific writing |
/brand | Brand voice, visual identity, messaging |
/graphic-design | Logos, icons, banners, slides, corporate identity |
Seven stages. Two require your input (brainstorm, plan). The rest run autonomously.
%%{init: {'theme': 'neutral'}}%%
flowchart LR
s0["Stage 0\nBranch Setup"] --> s1["Stage 1\nBrainstorm"]
s1 --> s15["Stage 1.5\nDesign System"]
s15 -. "UI only" .-> s2["Stage 2\nPlan"]
s1 --> s2
s2 --> s3["Stage 3\nImplement + Review"]
s3 --> s4["Stage 4\nDocumentation"]
s4 --> s5["Stage 5\nDeep Review"]
s5 --> done["Done"]
npx claudepluginhub conava/claude-devline --plugin devlineEnd-to-end development workflow: design → draft-plan → orchestrate → review → pr-create → pr-review → pr-merge
Persona-driven AI development team: orchestrator, team agents, review agents, skills, slash commands, and advisory hooks for Claude Code
AI-powered development workflow automation - Phase-based planning, implementation orchestration, preflight code quality checks with security scanning, ship-it workflow, and development principles generator for CLAUDE.md
Comprehensive feature development workflow with specialized agents for codebase exploration, architecture design, and quality review
VGV Wingspan - AI-native workflows following Very Good Ventures best practices.
A curated set of skills for each stage of development — propose, spec, design, plan, implement, ship.