Skip to content

tzachbon/srulik-toolkit / plugins/srulik-toolkit/skills/agent-swarm

agent-swarm

Verified

Coordinate delegated work through the child-agent capabilities available in the current harness. Use when the user asks to spawn agents, delegate, swarm, parallelize, race approaches, or when active instructions require an orchestrator and worker split. Does not require Traycer, a specific provider, or a fixed model.

FileKindSize
SKILL.mdskill md14.0 KB
agents/openai.yamlconfig208 B
graphs/pr-review.yamlconfig1.1 KB
graphs/task.yamlconfig8.8 KB
references/graph-spec.mdmarkdown19.5 KB
references/host-usage.mdmarkdown246 B
references/live-view.mdmarkdown2.6 KB
references/t3-code.mdmarkdown3.4 KB

graphs/pr-review.yaml

View on GitHub
name: pr-review
inputs:
  pr: 0
limits:
  max_agents: 8
  explore: true
writes:
  pr-comment:
    max: 1
    run: [gh, pr, comment, "${inputs.pr}", --body-file, "${file}"]
nodes:
  fetch:
    run: [gh, pr, diff, "${inputs.pr}"]
  review:
    kind: code-review
    agent: |
      Review this pull request diff for {item} defects only.
      Return JSON {"findings":[{"title":"","file":"","line":0,"why":""}]}; use an empty list when there are none.
    in: ${fetch.text}
    for_each: [bugs, perf, security]
    pick: { tier: strong }
    out: [findings]
  verify:
    kind: reasoning
    agent: |
      Try to refute this finding with evidence from the diff: {item}
      Return JSON {"confirmed":true|false,"evidence":""}.
    in: ${fetch.text}
    for_each: ${review.findings}
    pick: { tier: strong, differ_from: review }
    out: [confirmed, evidence]
    gate: confirmed == true
  report:
    kind: writing
    agent: |
      Rank the confirmed findings by severity and write a concise PR comment body.
      Each confirmed finding names its output file; read it for the evidence.
      Return JSON {"body":""}.
    needs: [verify]
    out: [body]
    write: pr-comment
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 472kUpdated Claude CodeCodexUnverifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 322kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 322kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is availableStars: 322kUpdated Claude CodeCodexVerifiedInstall