Skip to content

Adonis0123/adonis-skills / skills/agent-dispatch

agent-dispatch

Flagged

Choose the lightest agent setup for a coding, review, drafting or design-research task: do it yourself, fan out to 2-3 workers with independent parts across the Claude Code, Codex, Grok Build, Cursor or other CLIs and accounts on this machine, run a scoped architecture loop, or send one brief to independent researchers; pick a cross-model reviewer, test budget and cleanup; track dispatched work, external waits and user decisions on a Run Board. Use when work may need delegation, or the user asks to dispatch, fan out, parallelize, run several agents or accounts, get another AI's review or independent design opinions, or asks how dispatched work is going. Chinese triggers: 派活、并行、要不要多开几个 agent、分给多个 Claude 账号 / codex / grok、找另一个 AI 审、对比优秀设计、多方意见、进度看板、派出的任务进行到哪了。Not for unrelated read-only questions, trivial edits, research with no delegation, a single review of an existing diff (agentic-review-handoff), or the machine-wide session list (sideby sessions). Inside another named workflow, only size its workers.

FileKindSize
GLOSSARY.mdmarkdown2.1 KB
SKILL.mdskill md27.8 KB
evals/README.mdmarkdown7.6 KB
evals/README.zh-CN.mdmarkdown7.5 KB
evals/bench/compare.pyscript5.3 KB
evals/bench/run_bench.pyscript12.3 KB
evals/bench/tasks.jsonconfig6.6 KB
evals/bench/test_bench.pyscript4.4 KB
evals/build_plugin_eval.pyscript11.3 KB
evals/evals.jsonconfig31.4 KB
evals/results.mdmarkdown15.8 KB
evals/test_eval_harness.pyscript3.5 KB
evals/trigger-eval-set.jsonconfig1.6 KB
fixtures/probe-full.jsonconfig1.6 KB
fixtures/probe-single.jsonconfig690 B
fixtures/run-midrun/B9.jsonlother191 B
fixtures/run-midrun/deploy-log.txtmarkdown42 B
fixtures/run-midrun/run.jsonconfig1.8 KB
fixtures/run-sessions/B9.jsonlother191 B
fixtures/run-sessions/deploy-log.txtmarkdown42 B
fixtures/run-sessions/ended.jsonlother95 B
fixtures/run-sessions/run.jsonconfig2.1 KB
fixtures/run-sessions/sessions.jsonconfig804 B
fixtures/session-index.jsonconfig401 B
fixtures/sideby-stub/sessions.jsonconfig1.5 KB
fixtures/sideby-stub/sidebyexecutablescript4.1 KB
references/accounts.mdmarkdown10.4 KB
references/context-budget.mdmarkdown2.9 KB
references/fallbacks.mdmarkdown4.7 KB
references/launch.mdmarkdown16.1 KB
references/measure.mdmarkdown3.3 KB
references/research-brief.mdmarkdown1.3 KB
references/run-board.mdmarkdown48.7 KB
references/task-spec.mdmarkdown5.0 KB
scripts/board.cssother12.6 KB
scripts/board_interaction.jsscript3.7 KB
scripts/board_markdown.jsscript2.9 KB
scripts/board_render.pyscript17.2 KB
scripts/dispatch_board.pyscript95.3 KB
scripts/isolated_case.pyscript1.6 KB
scripts/probe_agents.pyscript12.9 KB
scripts/sideby_cli.pyscript3.2 KB
scripts/sideby_sessions.pyscript3.3 KB
scripts/test_billing_and_quota.pyscript10.9 KB
scripts/test_board_interaction.jsscript2.1 KB
scripts/test_board_markdown.jsscript2.9 KB
scripts/test_board_reload_state.jsscript2.7 KB
scripts/test_bug_regressions.pyscript4.7 KB
scripts/test_dispatch_board.pyscript68.9 KB
scripts/test_harness_limits.pyscript11.7 KB
scripts/test_lane_states.pyscript7.5 KB
scripts/test_probe_agents.pyscript19.2 KB
scripts/test_review_fixes.pyscript6.7 KB
scripts/test_rounds_and_watch.pyscript7.3 KB

fixtures/sideby-stub/sideby

View on GitHub
#!/usr/bin/env python3
"""Eval stand-in for sideby: answers from sessions.json beside it; nothing is sent anywhere.

Output shapes follow `sideby <command> --json` schemaVersion 1. Unsupported commands exit 2.
"""
import json
import sys
from datetime import datetime, timezone
from pathlib import Path

HERE = Path(__file__).resolve().parent
SEND_HELP = """sideby send <account|session> "<text>" [--image <path>]... [--lang en|zh] [--json]

Tell another running session something. <session> is a session id or its first 8 characters (see `sideby sessions`).
A Claude Code session gets it at once; Codex, Grok Build and pi need the user to paste one line sideby copies.
Exit: 0 delivered or kept for pasting; 1 no such running session or several to choose from; 2 malformed command line."""


def sessions():
    return json.loads((HERE / "sessions.json").read_text(encoding="utf-8"))


def out(data, as_json, text):
    print(json.dumps(data, ensure_ascii=False, indent=2) if as_json else text)
    return 0


def find(target):
    rows = [s for s in sessions()["sessions"]
            if s["sessionId"].startswith(target) or target in (s["account"], s.get("accountLabel"))]
    return rows


def send(args, as_json):
    if "--help" in args or "-h" in args:
        print(SEND_HELP)
        return 0
    words = [a for a in args if not a.startswith("--")]
    if len(words) < 2:
        print("sideby send: needs a target and the text", file=sys.stderr)
        return 2
    target, text = words[0], words[1]
    rows = find(target)
    if len(rows) != 1:
        print(f"sideby send: {'no running session' if not rows else 'several sessions'} match {target}", file=sys.stderr)
        return 1
    s = rows[0]
    msg_id = "m" + s["sessionId"][:6]
    file = f"~/.local/state/sideby/messages/{s['sessionId'][:8]}/{msg_id}.md"
    claude = s["family"] == "claude"
    receipt = {
        "id": msg_id, "to": s.get("label", s["sessionId"]), "toSessionId": s["sessionId"], "toAccount": s["account"],
        "status": "delivered" if claude else "paste-needed", "file": file, "attachments": [],
        "pasteText": f"Read the message sideby kept for you at {file}",
        "sentAt": datetime.now(timezone.utc).isoformat(timespec="seconds"),
    }
    if not claude:
        receipt["note"] = f"{s['family']} has no channel sideby can deliver to; paste the line into its tab."
    with (HERE / "sent.log").open("a", encoding="utf-8") as log:
        log.write(json.dumps({"to": s["sessionId"], "text": text}, ensure_ascii=False) + "\n")
    return out({"schemaVersion": 1, "message": receipt, "copied": not claude}, as_json,
               f"{receipt['status']}: {receipt['to']}")


def main(argv):
    as_json = "--json" in argv
    args = [a for a in argv if a != "--json"]
    cmd = args[:1]
    if cmd == ["sessions"] and args[1:2] == ["copy"] and len(args) > 2:
        rows = find(args[2])
        if len(rows) != 1:
            return 1
        return out({"schemaVersion": 1, "reference": rows[0]["label"]}, as_json, rows[0]["label"])
    if cmd == ["sessions"]:
        data = sessions()
        return out(data, as_json, "\n".join(f"{s['label']}  {s['status']}" for s in data["sessions"]))
    if cmd == ["send"]:
        return send(args[1:], as_json)
    if cmd == ["messages"]:
        return out({"schemaVersion": 1, "messages": []}, as_json, "no messages")
    if cmd == ["list"]:
        accounts = sorted({(s["family"], s["account"]) for s in sessions()["sessions"]})
        return out({"schemaVersion": 1, "accounts": [{"family": f, "ref": r, "sameLogin": []} for f, r in accounts]},
                   as_json, "\n".join(r for _, r in accounts))
    if args[:3] == ["config", "get", "aliases"]:
        return out({"schemaVersion": 1, "value": {}}, as_json, "{}")
    if cmd == ["ui"]:
        print("sideby ui: the Panel cannot open in this eval sandbox (no desktop)", file=sys.stderr)
        return 1
    if cmd in (["--version"], ["-v"]):
        print("sideby eval-stub")
        return 0
    print(f"sideby eval-stub: {' '.join(args) or '(no command)'} is not available here", file=sys.stderr)
    return 2


if __name__ == "__main__":
    sys.exit(main(sys.argv[1:]))
finishing-a-development-branchobra/superpowersUse when implementation is complete, all tests pass, and you need to decide how to integrate the workStars: 322kUpdated Claude CodeCodexVerifiedInstall
systematic-debuggingobra/superpowersUse when encountering any bug, test failure, or unexpected behavior, before proposing fixesStars: 322kUpdated Claude CodeCodexVerifiedInstall
test-driven-developmentobra/superpowersUse when implementing any feature or bugfix, before writing implementation codeStars: 322kUpdated Claude CodeCodexVerifiedInstall
skill-creatoranthropics/skillsCreate new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.Stars: 198kUpdated Claude CodeCodexVerifiedInstall