Skip to content

AL-JANEF/janef-forge / skills/engineering/delegation-discipline

delegation-discipline

Verified

Decide whether subagents, parallel agents, or agent teams are justified and, if so, delegate safely: one agent unless work is bounded, independent, and clearly owned; explicit outcome, ownership, constraints, and return format per worker; the integrating agent owns final correctness, security review, and verification. Use whenever delegation or parallel execution is being considered.

FileKindSize
SKILL.mdskill md2.1 KB
capability.jsonconfig1.7 KB

capability.json

View on GitHub
{
  "id": "delegation-discipline",
  "name": "Delegation Discipline",
  "version": "2.0.0",
  "domain": "engineering",
  "description": "Decide whether subagents, parallel agents, or agent teams are justified and, if so, delegate safely: one agent unless work is bounded, independent, and clearly owned; explicit outcome, ownership, constraints, and return format per worker; the integrating agent owns final correctness, security review, and verification. Use whenever delegation or parallel execution is being considered.",
  "triggers": [
    "subagent",
    "subagents",
    "sub-agent",
    "sub-agents",
    "delegate",
    "delegation",
    "delegating",
    "parallel agents",
    "parallelize",
    "parallelise",
    "agent team",
    "agent teams",
    "multi-agent",
    "multi agent",
    "spawn agents",
    "spawn an agent",
    "split the work",
    "fan out",
    "fan-out",
    "orchestrate agents",
    "worktree",
    "worktrees",
    "swarm",
    "background agent",
    "background agents",
    "in parallel",
    "concurrently investigate"
  ],
  "negative_triggers": [],
  "risk_level": "low",
  "context_cost": "small",
  "requires": [],
  "optional_with": [
    "context-efficiency"
  ],
  "conflicts_with": [],
  "verification_requirements": [
    "integrating agent re-verifies delegated results before completion",
    "no overlapping writes; every delegated result collected before the turn ends"
  ],
  "supported_hosts": [
    "claude-code",
    "codex"
  ],
  "references": [],
  "status": "stable",
  "responsibilities": [
    "delegation-gate",
    "parallel-work-contract"
  ],
  "priority": 44,
  "provenance": [
    "lean-code-engineer 0.1.0 references/agent-orchestration.md"
  ]
}
rea-analysis-optimizationmorluto/reaOptimize REA providers and shared analysis workflows for agent context, latency, CPU, and memory while preserving correctness and Evidence. Use for analysis bottlenecks and cache or query design; CI/test-suite optimization belongs to rea-ci-tests-audit.Stars: 471kUpdated Claude CodeCodexVerifiedInstall
rea-ci-tests-auditmorluto/reaAudit REA CI and test suites for correctness, fixture drift, false passes, and measured performance; use for suite or workflow investigations and efficiency changes, rather than ordinary feature testing or a single test failure.Stars: 471kUpdated Claude CodeCodexVerifiedInstall
rea-tool-designmorluto/reaAudit, investigate, design, or change REA investigation tools, CLI/MCP contracts, provider capabilities, and Evidence semantics.Stars: 471kUpdated Claude CodeCodexVerifiedInstall
ponytail-auditDietrichGebert/ponytailQuality audit of the whole repo: bugs, security, real load, missing tests, speed, and what to delete. Most important first.Stars: 194kUpdated Claude CodeCodexVerifiedInstall