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 andreaswasita/copilot-agents-dojo --skill dispatching-parallel-agentsgit clone --depth 1 https://github.com/andreaswasita/copilot-agents-dojoWrote 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/andreaswasita/copilot-agents-dojo/dispatching-parallel-agents)<a href="https://agentmods.dev/skills/andreaswasita/copilot-agents-dojo/dispatching-parallel-agents"><img src="https://agentmods.dev/badge/skills/andreaswasita/copilot-agents-dojo/dispatching-parallel-agents.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00017 | $0.01309 |
| Opus 5 | $0.00009 | $0.00655 |
| Sonnet 5 | $0.00003 | $0.00262 |
| Haiku 4.5 | $0.00002 | $0.00131 |
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 8d 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.
How it starts
The opening of the file, as written. The whole thing — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Dispatching Parallel Agents Skill
Runs multiple sub-agents concurrently when a plan contains independent subtasks with non-overlapping file boundaries. Each sub-agent receives a self-contained spec. Does NOT parallelize work with dependencies or shared mutable state — that path silently corrupts results.
When to Use
- The plan contains 2+ tasks with no dependency edges between them.
- Multiple research investigations or codebase explorations can run side-by-side.
- Multiple verification runs (lint, test, type-check) can run in parallel.
- User explicitly asks for parallel execution or to "speed this up".
- NOT for debugging (parallel agents mask timing bugs).
- NOT when tasks edit overlapping files or share mutable state.
Prerequisites
- An approved plan in
tasks/todo.mdwith task IDs and explicit dependencies. - The
taskCopilot tool available (or equivalent sub-agent mechanism). - Each candidate task has a precise file-boundary scope ("owns" a directory or file set).
- Integration test or verification step that exercises the combined result.
- The
view,edit,grep, andpowershellCopilot tools.
How to Run
1. From `tasks/todo.md`, pick tasks with no dependency edges between them.
2. Confirm each has a non-overlapping file scope.
3. Write a self-contained spec per agent (goal, files, DO NOT touch, verification).
4. Dispatch all sub-agents in one tool-call batch.
5. Collect each result; integrate.
6. Run an integration verification on the merged result.
7. Log failures and reasons in `tasks/lessons.md`.
Quick Reference
| Parallel-safe | Sequential-only |
|---|---|
| Independent API modules in different folders | Task B reads Task A's output |
| Separate research questions | Shared config edits |
| Per-package builds in a monorepo | Same-file mutations |
| Per-file lint or type-check passes | Migration scripts that order-depend |
| Spec field | Required |
|---|---|
| Goal | One sentence |
| Files owned | Directory or explicit list |
| Files forbidden | "DO NOT touch" list |
| Verification | Tests this agent must pass before returning |
| Return format | What the agent reports back |
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.
- 8d ago First seen · 141 lines · 17 tokens per session scan A 2ff9b5657b18
dispatching-parallel-agents is a skill published in the GitHub repository andreaswasita/copilot-agents-dojo (51 stars, last pushed today), licensed MIT. It adds 17 tokens to every session and 1,309 once invoked, about $0.0001 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
parallel
Use when two or more pieces of work are genuinely independent — disjoint files, no shared state, no ordering edge — and should fan out across subagents, then be gathered and reconciled under a combined test suite. Decides WHAT can run concurrently; NOT the isolation it runs in (that is worktrees), NOT the per-unit TDD…
agent-spawn
Use when you need to spawn a specialist sub-agent to handle a specific task domain without polluting the main session context.
decision-ledger
A session record for tracking unresolved decisions and drafting them into `.governance/claims/` when they are settled. It preserves both the decision and the reason behind it.
governance-bootstrap
A guided checklist for creating a project's governance system from scratch when no governance exists.
session-grounding
A session-start procedure for checking the current facts, scope, and work track in a governed project before taking action.
truth-first
A set of rules for writing technical conclusions and performing irreversible or state-changing operations. It requires evidence tied to file and line locations and restricts unsupported claims.