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 skills add tolgakisaogullari/SumelaOS --skill dispatching-parallel-agentsgit clone --depth 1 https://github.com/tolgakisaogullari/SumelaOSWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/tolgakisaogullari/sumelaos/dispatching-parallel-agents)<a href="https://agentmods.dev/skills/tolgakisaogullari/sumelaos/dispatching-parallel-agents"><img src="https://agentmods.dev/badge/skills/tolgakisaogullari/sumelaos/dispatching-parallel-agents/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/tolgakisaogullari/sumelaos/dispatching-parallel-agents"><img src="https://agentmods.dev/badge/skills/tolgakisaogullari/sumelaos/dispatching-parallel-agents.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What 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 5.1 | $0.00033 | $0.00744 |
| Opus 5 | $0.00016 | $0.00372 |
| Sonnet 5 | $0.00007 | $0.00149 |
| Haiku 4.5 | $0.00003 | $0.00074 |
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 10d 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
<usage_criteria>
- ALLOWED: 2+ independent test failures, bugs, research questions, or implementation tasks across completely different files/subsystems.
- ALLOWED: Read-only parallel research when each agent has a clearly separated question and no write scope.
- FORBIDDEN: Related failures, sequential dependencies, overlapping files, or tasks modifying the same configuration files (for example, both editing
package.json). - FORBIDDEN: Exploratory debugging where the root-cause domain is unknown; investigate sequentially first, then parallelize only after the failure surface is mapped. </usage_criteria>
<dispatch_workflow> Execute parallel dispatch using these strict steps:
-
IDENTIFY & ISOLATE DOMAINS:
- Group work by strictly independent file paths, subsystems, or read-only questions.
- If two agents might touch the same file, shared type, generated artifact, migration, lockfile, or config, DO NOT run them in parallel.
- Decide per agent whether the task is read-only or write-capable before dispatch.
-
CRAFT SAFE & COMPLIANT PROMPTS: Create one highly focused, self-contained task prompt per domain. Every prompt MUST include:
- Specific scope: the exact file, subsystem, or question.
- Clear goal: exact failing tests, error messages, or research output required.
- Required context: paste the minimum plan/spec/error details needed so the agent does not rely on hidden session history.
- Ownership: exact files the agent owns, or state "read-only; do not edit files."
- TDD & security mandate: "Follow the current TDD Mode: [Enabled/Skipped]. HOWEVER, if your fix touches AuthN, AuthZ, security boundaries, sensitive data, or input parsing, you MUST write a failing test first regardless of mode. You MUST strictly adhere to
secure-coding-standard." - Concurrency safety: "You are not alone in the codebase. Do not revert edits made by others. Do not change unrelated code. Run ONLY isolated checks for your scope. Do NOT run the global test suite. Do NOT run
git commit." - Staging rule: "If you changed files, stage ONLY your exact owned files using
git add <exact-file-path>. If this is read-only, do not stage anything and return findings only." - Output requirement: "Return root cause/findings, security considerations, verification run, and exact files changed/staged or confirm read-only."
-
DISPATCH:
- Launch all task agents concurrently only after every prompt has disjoint ownership and self-contained context.
-
INTEGRATE & GLOBAL VERIFY (ORCHESTRATOR'S JOB):
- Wait for ALL agents to return
DONE. - Read every agent summary and confirm changed files match assigned ownership.
- Run
git diff --stagedand/orgit diffto review the combined changes. - Spot-check the combined diff for systematic errors; parallel agents can each pass isolated checks while their combined changes interfere with each other.
- Invoke
verification-before-completionto run the full global verification safely in a single thread.
- Wait for ALL agents to return
-
COMPREHENSIVE REVIEW HANDOFF (MANDATORY GATE):
- Once global verification passes, invoke
requesting-code-reviewto evaluate the combined changes for quality andsecure-coding-standardcompliance before moving to completion. </dispatch_workflow>
- Once global verification passes, invoke
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.
- 10d ago First seen · 45 lines · 33 tokens per session scan A fb19e0dcbc50
dispatching-parallel-agents is a skill published in the GitHub repository tolgakisaogullari/SumelaOS (4 stars, last pushed 15d ago), licensed MIT. It adds 33 tokens to every session and 744 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…