mirror of
https://github.com/wshobson/agents.git
synced 2026-03-18 09:37:15 +00:00
fix(agent-teams): remove Context7 MCP dependency, align frontmatter with conductor patterns, bump to v1.0.1
Remove .mcp.json to eliminate external MCP dependency that likely caused plugin load failure. Add tools: field to all agents, version: field to all skills, matching conductor plugin patterns.
This commit is contained in:
Seth Hobson
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"name": "agent-teams",
|
||||
"version": "1.0.0",
|
||||
"version": "1.0.1",
|
||||
"description": "Orchestrate multi-agent teams for parallel code review, hypothesis-driven debugging, and coordinated feature development using Claude Code's Agent Teams",
|
||||
"author": {
|
||||
"name": "Seth Hobson",
|
||||
|
||||
@@ -1,6 +0,0 @@
|
||||
{
|
||||
"context7": {
|
||||
"command": "npx",
|
||||
"args": ["-y", "@upstash/context7-mcp"]
|
||||
}
|
||||
}
|
||||
@@ -116,7 +116,7 @@ Decomposes the feature into work streams with file ownership boundaries, gets yo
|
||||
/team-spawn research --name codebase-research
|
||||
```
|
||||
|
||||
Spawns 3 researchers to investigate different aspects in parallel — across your codebase (Grep/Read), the web (WebSearch/WebFetch), and library documentation (Context7 MCP). Each reports findings with citations.
|
||||
Spawns 3 researchers to investigate different aspects in parallel — across your codebase (Grep/Read) and the web (WebSearch/WebFetch). Each reports findings with citations.
|
||||
|
||||
### Security Audit
|
||||
|
||||
|
||||
@@ -1,6 +1,7 @@
|
||||
---
|
||||
name: team-debugger
|
||||
description: Hypothesis-driven debugging investigator that investigates one assigned hypothesis, gathering evidence to confirm or falsify it with file:line citations and confidence levels. Use PROACTIVELY when debugging complex issues with multiple potential root causes.
|
||||
description: Hypothesis-driven debugging investigator that investigates one assigned hypothesis, gathering evidence to confirm or falsify it with file:line citations and confidence levels. Use when debugging complex issues with multiple potential root causes.
|
||||
tools: Read, Glob, Grep, Bash
|
||||
model: opus
|
||||
color: red
|
||||
---
|
||||
|
||||
@@ -1,6 +1,7 @@
|
||||
---
|
||||
name: team-implementer
|
||||
description: Parallel feature builder that implements components within strict file ownership boundaries, coordinating at integration points via messaging. Use PROACTIVELY when building features in parallel across multiple agents with file ownership coordination.
|
||||
description: Parallel feature builder that implements components within strict file ownership boundaries, coordinating at integration points via messaging. Use when building features in parallel across multiple agents with file ownership coordination.
|
||||
tools: Read, Write, Edit, Glob, Grep, Bash
|
||||
model: opus
|
||||
color: yellow
|
||||
---
|
||||
|
||||
@@ -1,6 +1,7 @@
|
||||
---
|
||||
name: team-lead
|
||||
description: Team orchestrator that decomposes work into parallel tasks with file ownership boundaries, manages team lifecycle, and synthesizes results. Use PROACTIVELY when coordinating multi-agent teams, decomposing complex tasks, or managing parallel workstreams.
|
||||
description: Team orchestrator that decomposes work into parallel tasks with file ownership boundaries, manages team lifecycle, and synthesizes results. Use when coordinating multi-agent teams, decomposing complex tasks, or managing parallel workstreams.
|
||||
tools: Read, Glob, Grep, Bash
|
||||
model: opus
|
||||
color: blue
|
||||
---
|
||||
|
||||
@@ -1,6 +1,7 @@
|
||||
---
|
||||
name: team-reviewer
|
||||
description: Multi-dimensional code reviewer that operates on one assigned review dimension (security, performance, architecture, testing, or accessibility) with structured finding format. Use PROACTIVELY when performing parallel code reviews across multiple quality dimensions.
|
||||
description: Multi-dimensional code reviewer that operates on one assigned review dimension (security, performance, architecture, testing, or accessibility) with structured finding format. Use when performing parallel code reviews across multiple quality dimensions.
|
||||
tools: Read, Glob, Grep, Bash
|
||||
model: opus
|
||||
color: green
|
||||
---
|
||||
|
||||
@@ -48,7 +48,7 @@ If a preset is specified, use these configurations:
|
||||
**`research`** — Parallel codebase, web, and documentation research (default: 3 members)
|
||||
|
||||
- Spawn 3 `general-purpose` agents, each assigned a different research question or area
|
||||
- Agents have access to codebase search (Grep, Glob, Read), web search (WebSearch, WebFetch), and library documentation (Context7 MCP)
|
||||
- Agents have access to codebase search (Grep, Glob, Read) and web search (WebSearch, WebFetch)
|
||||
- Team name default: `research-team`
|
||||
|
||||
**`security`** — Comprehensive security audit (default: 4 members)
|
||||
|
||||
@@ -1,6 +1,7 @@
|
||||
---
|
||||
name: multi-reviewer-patterns
|
||||
description: Coordinate parallel code reviews across multiple quality dimensions with finding deduplication, severity calibration, and consolidated reporting. Use this skill when organizing multi-reviewer code reviews, calibrating finding severity, or consolidating review results.
|
||||
version: 1.0.1
|
||||
---
|
||||
|
||||
# Multi-Reviewer Patterns
|
||||
|
||||
@@ -1,6 +1,7 @@
|
||||
---
|
||||
name: parallel-debugging
|
||||
description: Debug complex issues using competing hypotheses with parallel investigation, evidence collection, and root cause arbitration. Use this skill when debugging bugs with multiple potential causes, performing root cause analysis, or organizing parallel investigation workflows.
|
||||
version: 1.0.1
|
||||
---
|
||||
|
||||
# Parallel Debugging
|
||||
|
||||
@@ -1,6 +1,7 @@
|
||||
---
|
||||
name: parallel-feature-development
|
||||
description: Coordinate parallel feature development with file ownership strategies, conflict avoidance rules, and integration patterns for multi-agent implementation. Use this skill when decomposing features for parallel development, establishing file ownership boundaries, or managing integration between parallel work streams.
|
||||
version: 1.0.1
|
||||
---
|
||||
|
||||
# Parallel Feature Development
|
||||
|
||||
@@ -1,6 +1,7 @@
|
||||
---
|
||||
name: task-coordination-strategies
|
||||
description: Decompose complex tasks, design dependency graphs, and coordinate multi-agent work with proper task descriptions and workload balancing. Use this skill when breaking down work for agent teams, managing task dependencies, or monitoring team progress.
|
||||
version: 1.0.1
|
||||
---
|
||||
|
||||
# Task Coordination Strategies
|
||||
|
||||
@@ -1,6 +1,7 @@
|
||||
---
|
||||
name: team-communication-protocols
|
||||
description: Structured messaging protocols for agent team communication including message type selection, plan approval, shutdown procedures, and anti-patterns to avoid. Use this skill when establishing team communication norms, handling plan approvals, or managing team shutdown.
|
||||
version: 1.0.1
|
||||
---
|
||||
|
||||
# Team Communication Protocols
|
||||
|
||||
@@ -1,6 +1,7 @@
|
||||
---
|
||||
name: team-composition-patterns
|
||||
description: Design optimal agent team compositions with sizing heuristics, preset configurations, and agent type selection. Use this skill when deciding team size, selecting agent types, or configuring team presets for multi-agent workflows.
|
||||
version: 1.0.1
|
||||
---
|
||||
|
||||
# Team Composition Patterns
|
||||
@@ -59,7 +60,7 @@ Best practices for composing multi-agent teams, selecting team sizes, choosing a
|
||||
- **Size**: 3 researchers
|
||||
- **Agents**: 3x `general-purpose`
|
||||
- **Default areas**: Each assigned a different research question, module, or topic
|
||||
- **Capabilities**: Codebase search (Grep, Glob, Read), web search (WebSearch, WebFetch), library documentation (Context7 MCP)
|
||||
- **Capabilities**: Codebase search (Grep, Glob, Read), web search (WebSearch, WebFetch)
|
||||
- **Use when**: Need to understand a codebase, research libraries, compare approaches, or gather information from code and web sources in parallel
|
||||
|
||||
### Security Team
|
||||
|
||||
@@ -149,7 +149,6 @@ Each researcher has access to:
|
||||
|
||||
- **Codebase**: `Grep`, `Glob`, `Read` — search and read local files
|
||||
- **Web**: `WebSearch`, `WebFetch` — search the web and fetch page content
|
||||
- **Library Docs**: Context7 MCP (`resolve-library-id`, `query-docs`) — look up current documentation for any library
|
||||
- **Deep Exploration**: `Task` with `subagent_type: Explore` — spawn sub-explorers for deep dives
|
||||
|
||||
### Task Template
|
||||
@@ -162,7 +161,6 @@ Description:
|
||||
Tools to prioritize:
|
||||
- Codebase: Grep/Glob/Read for local code analysis
|
||||
- Web: WebSearch/WebFetch for articles, examples, best practices
|
||||
- Docs: Context7 MCP for up-to-date library documentation
|
||||
Deliverable: Summary with citations (file:line for code, URLs for web)
|
||||
Output format: Structured report with sections, evidence, and recommendations
|
||||
```
|
||||
@@ -170,7 +168,6 @@ Description:
|
||||
### Variations
|
||||
|
||||
- **Codebase-only**: 3 researchers exploring different modules or patterns locally
|
||||
- **Documentation**: 3 researchers using Context7 to compare library APIs and patterns
|
||||
- **Web research**: 3 researchers using WebSearch to survey approaches, benchmarks, or best practices
|
||||
- **Mixed**: 1 codebase researcher + 1 docs researcher + 1 web researcher (recommended for evaluating new libraries)
|
||||
|
||||
@@ -178,8 +175,8 @@ Description:
|
||||
|
||||
```
|
||||
Researcher 1 (codebase): "How does our current auth system work? Trace the flow from login to token validation."
|
||||
Researcher 2 (docs): "Use Context7 to look up the latest NextAuth.js v5 API. How does it handle JWT and session management?"
|
||||
Researcher 3 (web): "Search for comparisons between NextAuth, Clerk, and Auth0 for Next.js apps. Focus on pricing, DX, and migration effort."
|
||||
Researcher 2 (web): "Search for comparisons between NextAuth, Clerk, and Auth0 for Next.js apps. Focus on pricing, DX, and migration effort."
|
||||
Researcher 3 (docs): "Look up the latest NextAuth.js v5 API docs. How does it handle JWT and session management?"
|
||||
```
|
||||
|
||||
## Security Team Preset
|
||||
|
||||
Reference in New Issue
Block a user