claude

agent-team-generic-copilot

Generic agent harness for Copilot CLI — pipeline agents, skills, plus the engine setup (re-run per update).

17 on GitHubby Agentic Coding Referencev0.4.13MITupdated 3 days ago
/

Plugin agent-team-generic-copilot from marketplace agent-team in woditschka/agentic-coding-reference. Commands read from the repo's manifest — 3 days ago.

What it installs

Skills (26)

  • adr-template

    Architecture Decision Record format, naming conventions, and when to create ADRs. Load when making or documenting architectural decisions. - claude-code - github-copilot - opencode - docs/adr/ version: "1.0" author: team

  • audit-agents

    Audit the agentic configuration for consistency, coherence, and conciseness. Load when modifying agent definitions, skills, or pipeline structure, or to verify cross-tool parity. - claude-code - github-copilot - opencode version: "2.0" author: team

  • audit-docs

    Audit the project's docs/ briefs against the high bar — each document on its own (principle form, enforceability) and in combination (cross-document coherence, contradictions, brief-vs-data agreement). Runs the doctor (deterministic structural gate) first, then the advisory judgment review, and repo

  • change-grading

    Grade a passing change for how much human attention it deserves before merge. Load when running the change-grader after the reviewer roster approves. Holds the full grading protocol: the five facets, worst-facet aggregation, the facets-rationale-verdict order, persistence, and scope/non-goals. - cla

  • code-quality-gate

    Build, test, format, and lint requirements that must pass before code review. Load when checking implementation completeness or running the quality gate. - claude-code - github-copilot - opencode - docs/testing-principles.md - docs/architecture-principles.md version: "1.0" author: team

  • code-quality-review

    Code-quality checklist — language-agnostic principles, design placement and workload fit against the project's recorded briefs, and the per-section slots a stack fills in. Load when conducting code quality reviews. - claude-code - github-copilot - opencode - docs/architecture-principles.md - docs/sy

  • derive-briefs

    Draft the project's docs/ briefs by surveying an existing codebase. Recovers requirements, design, vocabulary, and decisions from what the code demonstrably does, marking every statement with how it is known — derived, confirmed, or not recoverable. Load on a brownfield project whose briefs onboardi

  • design-validation

    Architectural validation checklist for feature approval. Load when validating that features fit into the existing architecture. - claude-code - github-copilot - opencode - docs/architecture-principles.md - docs/security-principles.md - docs/system-design.md - docs/prd.md - docs/ubiquitous-language.m

  • doc-sync

    Synchronize documentation with the current codebase. Fix drift between docs/prd.md, docs/system-design.md, and actual source code. - claude-code - github-copilot - opencode - docs/prd.md - docs/system-design.md version: "1.0" author: team

  • doctor

    Deterministic, blocking validation of the project's docs/ brief against the harness-project API: roster existence, required sections, data slots, naming conventions, channel invariants, and the reviewer roster. Load when onboarding a project, after a harness upgrade, or before starting pipeline work

  • document-writing

    How to write and review project documents: the language-agnostic writing standards, the five-document architecture and ownership boundaries, the document-structure model, cross-reference and maintenance rules, and the review checklist the doc-reviewer enforces. Load when authoring or reviewing any P

  • handoff-append

    The writer contract for the handoff log: how every pipeline agent appends records to .scratch/handoff.jsonl through scripts/handoff.py. Load when producing any handoff record — dispatch-start, a substantive record, or a consultation. The routing side lives in handoff-routing. - claude-code - github-

  • handoff-board

    The reader board for the handoff log: render each slice of .scratch/handoff.jsonl — header, review-convergence matrix, timeline — to the terminal via scripts/handoff.py view. Load when the user asks where the pipeline stands, for a slice status, or for a review-progress summary. The writer side live

  • handoff-routing

    Pipeline routing rules and handoff conditions between specialist agents: gates, recovery, and the root-applied procedures. Load when coordinating feature delivery, checking pipeline state, or determining which agent to invoke next. The writer side of the log lives in handoff-append. - claude-code -

  • init

    Scaffold the project-owned files this harness plugin needs — CLAUDE.md, .claude/settings.json, scripts/layout.toml, scripts/backlog.sh, the seven docs/ briefs, and the .gitignore block — from the plugin's bundled skeletons. Marketplace channel by construction; no clone of the reference needed. Run o

  • intake

    Run slice intake as a live discussion under the product expert's contract, then record the owner's request and decisions verbatim as an intake-decision record. Load when the user brings a feature request for discussion or invokes /intake. - claude-code - github-copilot - opencode - docs/prd.md versi

  • marketplace-setup

    Set up or upgrade this harness plugin's project-side half. Installs the engine sliver (scripts, schemas, templates) into your project and gitignores it, and refreshes the managed CLAUDE.md chapters. Run after installing the plugin and again after every plugin update.

  • new-feature

    Clear the scratch directory and start a fresh feature context. Load when starting a new feature or resetting pipeline state. - claude-code - github-copilot - opencode version: "1.0" author: team

  • next

    Reset feature context and recommend what to work on next from PRD coverage, git history, and the tracker connector. Load when the user asks "what's next" or invokes /next. - claude-code - github-copilot - opencode - docs/prd.md version: "1.1" author: team

  • prd-authoring

    PRD format conventions, boundary rules, and template references. Load when writing or reviewing product requirements. - claude-code - github-copilot - opencode - docs/prd.md - docs/ubiquitous-language.md version: "1.0" author: team

  • prepare-ship

    Close a feature before its push: fold the drafts the feature left above the publication boundary into the shape they ship in. An ADR absent from the remote's default branch is a draft: a later amendment of it folds into its body, and two drafts that record one decision merge. Transitional prose in t

  • review-workflow

    Review process overview, feedback tag definitions, and output format. Load when conducting or processing code reviews. - claude-code - github-copilot - opencode - docs/testing-principles.md - docs/architecture-principles.md - docs/security-principles.md version: "1.0" author: team

  • security-checks

    Security-review checklist, threat model, severity classification, and supply chain verification — language-agnostic, with per-section slots a stack fills in. Load when conducting security reviews. - claude-code - github-copilot - opencode - docs/security-principles.md version: "1.1" author: team

  • ship

    Run the quality gate, then commit staged and unstaged changes and push to the remote in one step. Load when the user asks to commit and push, or invokes /ship. - claude-code - github-copilot - opencode version: "1.0" author: team

  • tdd-workflow

    TDD cycle process and design-check decision tree for feature implementation. Load when implementing features using test-driven development. - claude-code - github-copilot - opencode - docs/system-design.md - docs/ubiquitous-language.md - docs/architecture-principles.md - docs/testing-principles.md -

  • test-review

    Test quality checklist, security-testing requirements, and dynamic-analysis expectations — language-agnostic, with per-section slots a stack fills in. Load when conducting test reviews. - claude-code - github-copilot - opencode - docs/testing-principles.md - docs/system-design.md version: "1.0" auth

Subagents (11)

  • Change Grader

    Grade a passing change for how much human attention it deserves before merge. Terminal, advisory node dispatched after the reviewer roster approves. Reads the diff and the deterministic feature row, emits five facets (skim/scrutinize/unknown) with notes, a rationale, and a skim/scrutinize verdict na

  • Code Quality Reviewer

    Review code for readability and maintainability following the project's code-quality conventions. Checks naming conventions, function design, module structure, error handling patterns, and code organization.

  • Documentation Reviewer

    Review documentation for coherence, structural correctness, and writing quality. Validates PRD, system-design, and ADRs against the checklist in the document-writing skill.

  • Feature Implementer Routine

    Checklist-tier variant of feature-implementer with identical doctrine. Selected only when the router's ledger-derived tier names routine work; never dispatch it directly.

  • Feature Implementer

    Implement features following Test-Driven Development (TDD) and Domain-Driven Design (DDD) practices. Reads current feature scope, starts from the requirement's test list, writes tests first, then implements code to pass those tests.

  • Pipeline Coordinator

    Orchestrates the feature delivery pipeline. Use for `escalate` decisions and intake neither the `intake` skill nor the `next` triage classified. - read - search - runTerminalCommand

  • Product Requirements Expert

    Author, refine, and validate product requirements in the PRD. Dispatched on a recorded intake-decision, in consultation mode on a requirement gap, for the next slice of a split, or to revise a REQ.

  • Review Planner

    Resolve a gray review-plan into a concrete reviewer roster. Dispatched only when the deterministic engine defers a small, clean production change it cannot classify. Reads the diff and appends the resolving review-plan record. - read - search - runTerminalCommand

  • Security Reviewer

    Review code for security vulnerabilities. Checks for OWASP top 10 issues, injection attacks, sensitive data exposure, authentication flaws, and stack-specific security concerns.

  • System Design Expert

    Principal-engineer view of the codebase. Triages every slice against durable memory and is consulted by the implementer on demand. Maintains docs/system-design.md and docs/adr/, crystallizing only the load-bearing parts of the cross-feature mental model.

  • Test Reviewer

    Review test quality, coverage, and adherence to the testing pyramid. Validates that tests are thorough, mocking is minimized, and edge cases are covered.

View source on GitHub

More from woditschka/agentic-coding-reference

All 6 plugins →

Go agent harness for Claude Code — pipeline agents, skills, continuation hook, plus the engine setup (re-run per update).

28 skills · 11 agents · hooks

17

Java Spring Boot agent harness for Claude Code — pipeline agents, skills, continuation hook, plus the engine setup (re-run per update).

28 skills · 11 agents · hooks

17

Go agent harness for Copilot CLI — pipeline agents, skills, plus the engine setup (re-run per update).

28 skills · 11 agents

17

Java Spring Boot agent harness for Copilot CLI — pipeline agents, skills, plus the engine setup (re-run per update).

28 skills · 11 agents

17

Generic agent harness for Claude Code — pipeline agents, skills, continuation hook, plus the engine setup (re-run per update).

26 skills · 11 agents · hooks

17

Maintain agent-team-generic-copilot?

This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.

claude & codex plugins6 plugins