Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/thiientv/godmode/dispatching-parallel-agentsnpx skills add thiientv/godmode --skill dispatching-parallel-agentsgit clone --depth 1 https://github.com/thiientv/godmodeWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00070 | $0.00348 |
| Opus 5 | $0.00035 | $0.00174 |
| Sonnet 5 | $0.00014 | $0.00070 |
| Haiku 4.5 | $0.00007 | $0.00035 |
Grade A, and why
dispatching-parallel-agents scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Dispatching Parallel Agents
Parallelism reduces elapsed time only when it does not multiply integration ambiguity.
Dispatch checklist
- Define the shared outcome and acceptance evidence.
- Map dependencies and identify the critical path.
- Split by coherent responsibility, not arbitrary file count.
- Give every agent a disjoint write set and a narrow prompt.
- State repository rules, interfaces, expected artifacts, and stop conditions.
- Decide who integrates, resolves conflicts, and runs the final proof.
Good units are an independent reference/eval update, a script with its tests, or separate adapters with a stable manifest contract. Bad units are two agents editing the same public skill, guessing an interface that another agent owns, or investigating one symptom with competing hypotheses.
Handoff contract
Each agent returns:
- files changed;
- decisions and assumptions;
- commands run and exact result;
- known gaps or conflicts;
- follow-up needed by the integrator.
Treat agent output as untrusted work product. Read the diff and rerun the relevant checks before merging. Do not claim the aggregate task is complete because every agent reported success.
Completion condition
Parallel work is integrated only after interface compatibility, conflict resolution, focused checks, and one fresh aggregate verification pass.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 48 lines · 70 tokens per session scan A f1a2dfddf101
dispatching-parallel-agents is a skill published in the GitHub repository thiientv/godmode (93 stars, last pushed 7d ago), licensed MIT. It adds 70 tokens to every session and 348 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
agent-reproduce-feature
Use when reproducing an existing Codex or Claude Code feature in Qwen Code or another agent CLI by choosing a reference agent, capturing HTTP request bodies, prompts, tool/function schemas, terminal output, and then implementing the matching behavior in the target repo.
agent-evaluation-reporting
Use when summarizing agent evaluations where autonomous, assisted, failed, timed-out, or invalid outcomes must remain distinct and comparable.
coordinate
Coordinate a small team of Qwen Code teammates with enforced read-only workers, an optional worktree-pinned writer, shared tasks, peer messages, and existing Agent View tabs. Invoke explicitly with /coordinate.
ifixai
Guide the user through an independent iFixAi audit of their own agent, checking whether it does the job it is supposed to do given their business rules and org structure. Prefer pointing it at the user's REAL deployed agent over its HTTP endpoint (its actual tools, retrieval, and governance) with --provider http…
workflow-runner
在 Claude Code / OpenClaw / Cursor 中直接运行 agency-orchestrator YAML 工作流——无需 API key，使用当前会话的 LLM 作为执行引擎。当用户提供 .yaml 工作流文件或要求多角色协作完成任务时触发。.
om-create-agents-md
Create or rewrite AGENTS.md files for Open Mercato packages and modules. Use this skill when adding a new package, creating a new module, or when an existing AGENTS.md needs to be created or refactored. Ensures prescriptive tone, the Always/Ask First/Never/Validation Commands boundary structure, MUST-style rules…