Agent Skills › boshu2/agentops › swarm

swarm

GitHub

Swarm 技能用于通过调用者选择的执行器，精确且仅一次地分发已证明写入范围不相交的显式离散数据包。它确保并行任务独立运行，收集结果并停止，适用于需要严格隔离和一次性执行的场景。

images/gemini/skills/swarm/SKILL.md boshu2/agentops

Trigger Scenarios

swarm dispatch disjoint packets parallel explicit tasks

Install

npx skills add boshu2/agentops --skill swarm -g -y

More Options

Non-standard path

npx skills add https://github.com/boshu2/agentops/tree/main/images/gemini/skills/swarm -g -y

Use without installing

npx skills use boshu2/agentops@swarm

指定 Agent (Claude Code)

npx skills add boshu2/agentops --skill swarm -a claude-code -g -y

安装 repo 全部 skill

npx skills add boshu2/agentops --all -g -y

预览 repo 内 skill

npx skills add boshu2/agentops --list

SKILL.md

Frontmatter

{
    "name": "swarm",
    "consumes": [
        "explicit-disjoint-packets"
    ],
    "metadata": {
        "tier": "execution",
        "effects": [
            "invoke_selected_executor"
        ],
        "disposition": "keep_optional_adapter",
        "capabilities": [
            "dispatch_once"
        ],
        "dependencies": [],
        "canonical_status": "canonical"
    },
    "produces": [
        "per-packet-results"
    ],
    "practices": [
        "team-topologies",
        "design-by-contract"
    ],
    "context_rel": [],
    "description": "Dispatch explicit disjoint packets exactly once through a caller-selected executor. Triggers: \"swarm\", \"dispatch disjoint packets\", \"parallel explicit tasks\".",
    "hexagonal_role": "driving-adapter",
    "user-invocable": true,
    "output_contract": "per-packet candidate, evidence, or error",
    "skill_api_version": 1
}

Swarm

Swarm exposes one optional factory port:

dispatch_once(explicit_disjoint_packets, executor)
  -> per-packet candidate | evidence | error

The caller supplies every complete packet, proves their write scopes disjoint, and chooses the executor. Swarm dispatches each packet once, preserves packet and context identities, collects results, and stops.

Write scopes must be workspace-relative and canonical — symlink-resolved and already normalized. The disjointness check is lexical: it case-folds prefixes so scopes differing only by case are treated as a collision (safe on case-insensitive filesystems), but it cannot see a symlink that aliases two scopes onto one target. Supplying non-canonical or symlinked scopes forfeits the disjointness guarantee; a non-empty write_scope.exclude is rejected, not silently ignored, because the proof cannot honor it.

Exactly-once dispatch over proven-disjoint scopes is why parallel failures stay independent: no packet can observe, block, or corrupt another, so N packets yield N factual results about N experiments rather than one tangle. Those results are not semantic verdicts.

Named failure mode — partial-batch launch: dispatching valid packets before discovering an invalid one, leaving the batch half-run; validate the entire batch before the first call.

Anti-pattern: re-dispatching a packet whose executor returned an error. Corrective: return the error as that packet's factual result; retry is the caller's decision, not the dispatcher's.

The reference implementation is scripts/dispatch_once.py. It validates the entire explicit batch before the first call, invokes the supplied executor exactly once for each packet, and returns executor exceptions as factual per-packet errors.

Swarm's own effect is invoking the selected executor once per packet; the real blast radius rides on the packets. Each packet's transitive effects — whatever its executor writes, runs, or reaches — are the caller's to declare on the packet, not Swarm's to bound.

Swarm does not select work, create packets, schedule from a backlog, persist a queue, claim ownership, retry, validate, integrate, close, use Git, or deliver. Executor failures remain executor evidence and cannot become core phase or verdict state. The adapter cannot select AgentOps semantics, issue a binding verdict, or turn factory completion into delivery or validation proof.