Professional agentic workflow: 7 agents (planner/builder/triage/impact/shipper/reviewer/debugger), 7 skills, quality hooks. Speak naturally — agents route automatically.
Invoke the `builder` agent defined in `agents/builder.md`.
Invoke the `impact` agent defined in `agents/impact.md`.
Invoke the `planner` agent defined in `agents/planner.md`.
Save current session state for resuming later.
Invoke the `shipper` agent defined in `agents/shipper.md`.
Use this agent for all NestJS backend work across CampX microservices. Trigger on: entity, migration, service, controller, DTO, module, TypeORM, repository, guard, decorator, interceptor, NestJS, backend, server, database, schema, API endpoint, REST API, campx-exams-server, campx-admin-server, campx-api-gateway, campx-lms-server, campx-hrms-server, campx-paymentx-server, campx-tenant-server, campx-square-server, campx-scheduler-server. <example> Context: User wants to add a backend feature. user: "Add a new endpoint to get student GPA history in campx-exams-server" assistant: "I'll use the backend-agent to implement this NestJS endpoint." <commentary> User wants backend work. backend-agent handles NestJS entities, services, controllers, DTOs, and migrations. </commentary> </example> <example> Context: User asks about a database entity. user: "How does the StudentMarks entity work? What are its relations?" assistant: "I'll use the backend-agent to read and explain the entity structure." <commentary> User is asking about a TypeORM entity. Use backend-agent. </commentary> </example> <example> Context: User wants to write a migration. user: "Write a migration to add a remarks column to the exam_results table" assistant: "I'll use the backend-agent to write this TypeORM migration." <commentary> User wants a DB migration. backend-agent handles schema changes via migration files. </commentary> </example>
Use this agent when the user wants to implement an approved plan. Trigger on: build it, implement, let's build it, start building, start coding, go ahead and implement, proceed with implementation, approved go ahead, execute tasks. Do NOT use when no plan exists (run planner first). Do NOT use for shipping (use shipper). <example> Context: User has an approved plan and wants to implement it. user: "build it" assistant: "I'll use the builder agent to implement the approved plan." <commentary> User wants to implement a plan. Use the builder agent. </commentary> </example> <example> Context: User approves a plan. user: "looks good, go ahead and implement this" assistant: "I'll use the builder agent to execute the implementation." <commentary> User approved a plan. Use the builder agent. </commentary> </example>
Use PROACTIVELY when the user wants to debug or fix a bug. Trigger on: debug this, fix the bug, what's wrong, why is this failing, crash, error, broken, not working, help me debug, trace the issue, investigate this error, something's wrong, what went wrong, fix this issue, test is failing, page crashes, endpoint returns error.
Use this agent for all React frontend work across CampX microfrontends. Trigger on: React, component, page, UI, frontend, microfrontend, hook, context, MUI, Material UI, form, table, modal, drawer, button, layout, routing, campx-exams-web, campx-admin-web, campx-evaluator-web, campx-lms-web, campx-hrms-web, campx-payments-web, campx-tenant-web, campx-ums-web, campx-student-central-web, shared component, @campxdev/shared, @campxdev/react-blueprint. <example> Context: User wants to build a React page. user: "Build a student GPA history page in campx-exams-web" assistant: "I'll use the frontend-agent to build this React page." <commentary> User wants frontend work. frontend-agent handles React components, pages, hooks, and UI. </commentary> </example> <example> Context: User asks about a component. user: "How does the GradeCard component work?" assistant: "I'll use the frontend-agent to find and explain this component." <commentary> User is asking about a React component. Use frontend-agent. </commentary> </example> <example> Context: User wants to add a UI feature. user: "Add a filter dropdown to the marks table in the evaluator portal" assistant: "I'll use the frontend-agent to add this UI feature." <commentary> User wants a UI addition. Use frontend-agent. </commentary> </example>
Use this agent when the user wants to understand the blast radius of a code change. Trigger on: before I change X, what breaks if, blast radius, check impact, is it safe to change, what's affected, will this break anything, what breaks if I modify, safe to refactor, before refactor, before I delete. Also trigger when user mentions changing: moderation, grace, grafting, grading, GPA, memo, transcript. <example> Context: User wants to check impact before a change. user: "Before I change the grading logic, what's the blast radius?" assistant: "I'll use the impact agent to trace what's affected by this change." <commentary> User wants blast radius analysis. Use the impact agent. </commentary> </example> <example> Context: User wants to know what breaks. user: "What breaks if I modify the moderation stage entity?" assistant: "I'll use the impact agent to analyze downstream pipeline effects." <commentary> User wants impact analysis on an exam pipeline entity. Use the impact agent. </commentary> </example>
Analyzes blast radius and downstream impact of code changes across the CampX exam pipeline. Use PROACTIVELY when user says: 'before I change', 'what breaks if', 'blast radius', 'check impact', 'is it safe to change', 'what's affected', 'will this break anything', 'safe to refactor', 'before I delete', 'before I modify'. Also trigger when user mentions changing: moderation, grace, grafting, grading, GPA, memo, transcript, exam pipeline stages.
Use PROACTIVELY at the start of every new CampX feature, task, or bug fix. Trigger on: 'new feature', 'new task', 'I want to build', 'start work on', 'new bug fix', 'I need to', 'we need to add', 'build X', 'fix X in campx'. Asks branch + repos + env before brainstorming. Outputs orbit new command. Waits for workspace to be up before reading code.
Runs quality gate then commits, pushes, and creates a PR for CampX repos. Use PROACTIVELY when user says: 'ship it', 'ship this', 'done push it', 'commit and push', 'create a PR', 'ready to ship', 'push this', 'let's merge this', 'done coding', 'create pull request', 'merge this'. Runs tsc + lint + tests before committing. Never ships without passing quality gate.
Switches CampX backend environment config using merge-env.sh. Use PROACTIVELY when user says: 'switch env', 'switch to staging', 'switch to prod', 'switch to dev', 'change environment', 'use staging', 'use production', 'point to prod', 'point to staging'. Do NOT use for frontend env changes or Docker config.
Investigates and resolves CampX support tickets and data issues. Use PROACTIVELY when user says: 'I got a ticket', 'support ticket', 'student can't see', 'wrong data', 'wrong marks', 'wrong grades', 'wrong branch', 'someone reported', 'client reported', 'data fix', 'data issue', 'triage this', pastes a campx.frappe.cloud link, or reports any student/tenant data problem. Fetches ticket from Frappe or GitHub, classifies severity, finds matching z-migration, reads affected entities, generates verification SQL queries — all in one pass.
Modifies files
Hook triggers on file write and edit operations
Uses power tools
Uses Bash, Write, or Edit 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.
No model invocation
Executes directly as bash, bypassing the AI model
No model invocation
Executes directly as bash, bypassing the AI model
Professional agentic workflow for Claude Code: 5 agents, 7 skills, quality hooks.
Speak naturally — agents route automatically to the right workflow.
Preloaded into agents — always available, fire on natural language triggers:
Quick slash-shortcuts for manual workflows:
/workflow:plan [description] — Invoke planner/workflow:triage [description] — Invoke triage/workflow:ship — Invoke quality gate/workflow:save-session — Save session stateSecurity-first hooks auto-enforced:
claude plugin install https://github.com/ramchanderpeddada/workflow-plugin
Just say: "I need to build a fee reminder system" → planner announces and asks clarifying questions → produces a structured plan.
After plan is approved: "build it" → builder announces, implements per the plan, writes tests, creates PR.
"Got a ticket about wrong marks" → triage announces, classifies severity, finds z-migrations, generates SQL verification queries.
Before refactoring: "is it safe to change moderation logic" → impact announces, traces 9-stage pipeline, shows downstream effects.
4.0.0 — Initial plugin architecture.
Built for professional agentic workflows.
npx claudepluginhub ramchanderpeddada/workflow-plugin --plugin workflowComprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
Harness-native ECC operator layer - 67 agents, 271 skills, 92 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses
Persistent file-based planning for AI coding agents. Crash-proof markdown plans (task_plan.md, findings.md, progress.md) that survive context loss and /clear, with an opt-in completion gate and multi-agent shared state. Manus-style. Works with Claude Code, Codex CLI, Cursor, Kiro, OpenCode and 60+ agents via the SKILL.md standard. Includes Arabic, German, Spanish, and Chinese (Simplified and Traditional).
Superpowers Plus core skills library for Claude Code: planning, execution routing, TDD, debugging, and collaboration workflows
A growing collection of Claude-compatible academic workflow bundles. Covers scientific figures, manuscript writing and polishing, reviewer assessment, citation retrieval, data availability, paper reading, literature search, response letters, paper-to-PPTX conversion, and evidence-grounded Chinese invention patent drafting. Rules are organized as reusable skill folders with explicit workflows and quality checks.
Tools to maintain and improve CLAUDE.md files - audit quality, capture session learnings, and keep project memory current.