hjemmesidekongen/agent-teams
plugins/kronen/skills/agent-teams/SKILL.md
Parallel team execution patterns for multi-agent workflows. Use when planning parallel agent dispatch, choosing team compositions (review, debug, feature, research, security teams), or integrating with Agent Teams experimental API. Covers file ownership rules, task coordination, and integration patterns.
development
Updated Apr 5, 2026
$ install --global
skillsauthnpx skillsauth add hjemmesidekongen/ai agent-teamsInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Apr 5, 2026, 5:42 PM40.0s2 files scanned
SKILL.md
- name:
- agent-teams
- description:
- |
- user_invocable:
- true
- interactive:
- true
- depends_on:
- []
- reads:
- []
- writes:
- []
- type:
- data_validation
- - name:
- team_dispatched
- verify:
- Team composition selected and agents dispatched with file ownership
- fail_action:
- Verify team preset matches use case and retry dispatch
- on_fail:
- Re-evaluate team composition
- on_pass:
- Team dispatched with file ownership isolation
- model_tier:
- senior
- origin:
- original
- ported_date:
- 2026-03-09
- iteration:
- 1
- changes:
- ["initial creation"]
Agent Teams
Patterns for parallel agent execution using Claude Code's Agent Teams feature or manual parallel dispatch via the Agent tool.
Team Presets
| Team | Agents | Use Case | |------|--------|----------| | Review | 3 parallel reviewers (security, performance, architecture) | Code review, PR review | | Debug | N investigators (one per hypothesis) | Root cause investigation | | Feature | 1 lead + 2 implementers | Feature development with file ownership | | Fullstack | 1 lead + frontend + backend + test | End-to-end feature build | | Research | 3 general-purpose agents | Parallel research questions | | Security | 4 reviewers (OWASP, auth, deps, config) | Security audit | | Migration | 1 lead + 2 implementers + 1 reviewer | Large-scale migration |
File Ownership (Cardinal Rule)
One owner per file — no concurrent modifications. Period.
- When files must be shared: designate one owner, others request changes sequentially
- Extract interface contracts at boundaries (owned by lead, read-only for implementers)
- Use the
file-ownershipskill to decompose work into conflict-free streams
Task Coordination
- Minimize dependency chain depth — wide, shallow graphs beat deep chains
- Use
blockedBy/blocksonly for true dependencies - Design interface contracts at integration boundaries before implementation
Integration Patterns
| Pattern | When | How | |---------|------|-----| | Vertical slice | Low coupling between features | Each agent builds full UI + API + tests for one feature | | Horizontal layer | Shared data model | Each agent owns one layer across features | | Hybrid | Mixed coupling | Vertical for independent features, horizontal for shared |
Current Status
Agent Teams requires CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1 and tmux or iTerm2. The patterns in this skill work regardless — they apply to both native Agent Teams and manual parallel dispatch via the Agent tool.
For full team sizing, display modes, and coordination strategies: references/process.md.
Related Skills
hjemmesidekongen/brand-strategy
development
VerifiedTrustedCommunity
Creates a brand from scratch through market research and interactive sparring. Runs competitive research via Perplexity, then guides the user through positioning, audience, voice, values, and content pillars. Produces the full brand guideline set at .ai/brand/{name}/. Use when building a new brand, defining brand strategy for a product, or when /våbenskjold:create is invoked.
SKILL.mdUpdated Apr 5, 2026
hjemmesidekongen/brand-loader
testing
VerifiedTrustedCommunity
Loads brand guidelines from .ai/brand/{name}/ and makes them available to the current context. Progressive disclosure: L1 confirms brand exists, L2 loads summary, L3 loads specific files on demand. Use when a downstream skill or user needs brand context, or when /våbenskjold:apply is invoked.
SKILL.mdUpdated Apr 5, 2026
hjemmesidekongen/brand-evolve
documentation
VerifiedTrustedCommunity
Guided reinvention of an existing brand guideline. Loads current brand from .ai/brand/{name}/, identifies what to keep vs change, and walks the user through targeted evolution. Preserves brand equity while updating positioning, voice, or values. Use when refreshing a brand or when /våbenskjold:evolve is invoked.
SKILL.mdUpdated Apr 5, 2026
hjemmesidekongen/brand-audit
development
VerifiedTrustedCommunity
Codifies an existing brand from materials, samples, and references. Analyzes provided content to extract voice patterns, values, and positioning. Produces the same guideline format as brand-strategy. Use when a brand already exists but isn't documented, or when /våbenskjold:audit is invoked.
SKILL.mdUpdated Apr 5, 2026