hjemmesidekongen/agent-dispatcher
plugins/smedjen/skills/agent-dispatcher/SKILL.md
Dispatches decomposed subtasks to worker agents with tier-appropriate model assignment. Enforces file ownership, includes reference_paths from project profile for knowledge loading, collects reports, retries failures once at the same tier, then escalates to the next tier. Called after task-decomposer and tier-assignment complete.
data-ai
Updated Apr 5, 2026
$ install --global
skillsauthnpx skillsauth add hjemmesidekongen/ai agent-dispatcherInstall 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, 5:27 PM24.3s2 files scanned
SKILL.md
- name:
- agent-dispatcher
- description:
- >
- user_invocable:
- false
- interactive:
- false
- model_tier:
- senior
- type:
- data_validation
- - name:
- no_ownership_violations
- verify:
- No two agents wrote to the same file
- fail_action:
- Log conflict and re-dispatch with corrected ownership
- on_fail:
- Dispatch incomplete — resolve failures before proceeding to completion gate
- on_pass:
- All agents dispatched and reported — ready for completion gate
- origin:
- smedjen
- inspired_by:
- SA-D009 + SA-D011 decisions
- ported_date:
- 2026-03-09
- iteration:
- 2
- changes:
- Added reference_paths, prerequisites checkpoint, ordering invariants. Removed pipeline dependency.
Agent Dispatcher
Coordinates parallel agent execution. Each agent gets an exclusive file list, a model tier, relevant skill references, and a focused prompt.
Hard rules
- NEVER dispatch before file ownership is resolved
- NEVER let an agent self-grade — completion-gate reviews all work
- NEVER skip the same-tier retry before escalating
Prerequisites (SA-D011)
Before dispatching, verify: (1) decomposition exists, (2) file ownership resolved.
Dispatch Flow
- Read decomposed subtasks with tier assignments
- Load
.ai/project-map.ymlfor reference_paths - Group by dependency level — independent tasks run in parallel
- Assign file ownership (no shared files between agents)
- Build agent prompt with reference_paths from profile's skills field
- Dispatch via Agent tool at assigned tier
- Collect reports; retry once at same tier, then escalate
- Write dispatch records
For reference_paths resolution, prompt templates, retry flow, wave construction,
and dispatch record schema → 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