Borrowing it
Nothing to install: this file belongs to irahardianto/rugged-gemini. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/irahardianto/rugged-gemini/main/.gemini/skills/parallel-dispatch-dag/SKILL.mdgit clone --depth 1 https://github.com/irahardianto/rugged-geminiWrote 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/irahardianto/rugged-gemini/parallel-dispatch-dag)<a href="https://agentmods.dev/skills/irahardianto/rugged-gemini/parallel-dispatch-dag"><img src="https://agentmods.dev/badge/skills/irahardianto/rugged-gemini/parallel-dispatch-dag.svg" alt="Measured on agentmods" 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 | $0.00049 | $0.01846 |
| Opus 5 | $0.00024 | $0.00923 |
| Sonnet 5 | $0.00010 | $0.00369 |
| Haiku 4.5 | $0.00005 | $0.00185 |
Grade A, and why
parallel-dispatch-dag 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 — 181 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Parallel Dispatch: Dependency Graph
Build a DAG from scope cards. Topological sort into levels. Dispatch all nodes at the same level in parallel.
When to Invoke
- After scope cards are produced by
parallel-dispatch-decomposition - Before dispatching any agents within a primitive
- When re-planning after a sub-task failure
Graph Construction
Nodes
Each scope card becomes a node in the DAG:
- ID:
@<agent-type>[<scope>] - Type:
write(modifies files) orread(read-only analysis) - Phase: The primitive this node belongs to (SCOUT, DESIGN, BUILD, REVIEW, etc.)
Edges
Each "Blocked By" or "Hard Dependencies" entry in a scope card becomes a directed edge:
- Edge direction: dependency → dependent (producer → consumer)
- Only hard dependencies create edges. Soft dependencies are advisory.
Construction Algorithm
- Create a node for each scope card
- For each node, read its "Hard Dependencies" and "Blocked By" fields
- Create an edge from each dependency to this node
- Validate: every referenced dependency exists as a node (no dangling references)
Topological Sort
Group nodes into levels based on their depth in the dependency graph:
- Level 0: Nodes with zero incoming edges (no dependencies). These execute first.
- Level N: Nodes whose dependencies are all in levels 0 through N-1.
All nodes at the same level are independent of each other and can be dispatched in parallel.
Sort Algorithm
1. Initialize in-degree count for each node
2. Enqueue all nodes with in-degree = 0 → Level 0
3. For each node in current level:
a. Remove its outgoing edges (decrement in-degree of dependents)
b. If any dependent's in-degree reaches 0 → add to next level
4. Repeat until all nodes assigned
5. If unassigned nodes remain → cycle detected → ABORT
DAG Output Format
Present the execution plan as a leveled dispatch table:
## Execution DAG
### Level 0 (no dependencies — dispatch in parallel)
| Node | Agent | Scope | Type | Deliverables |
|------|-------|-------|------|-------------|
| 1 | @scout | [auth] | read | Auth pattern research |
| 2 | @scout | [tasks] | read | Task engine research |
| 3 | @scout | [infra] | read | Infrastructure research |
### Level 1 (depends on Level 0 — dispatch after Level 0 completes)
| Node | Agent | Scope | Type | Blocked By | Deliverables |
|------|-------|-------|------|-----------|-------------|
| 4 | @architect | [api-contracts] | write | 1, 2 | API contract definitions |
| 5 | @architect | [data-model] | write | 1, 2, 3 | Data model design |
### Level 2 (depends on Level 1 — dispatch after Level 1 completes)
| Node | Agent | Scope | Type | Blocked By | Deliverables |
|------|-------|-------|------|-----------|-------------|
| 6 | @backend-engineer | [auth] | write | 4 | Auth feature implementation |
| 7 | @backend-engineer | [tasks] | write | 4, 5 | Task feature implementation |
| 8 | @frontend-engineer | [auth-ui] | write | 4 | Auth UI components |
| 9 | @frontend-engineer | [task-ui] | write | 4, 5 | Task UI components |
### Level 3 (depends on Level 2 — dispatch after Level 2 completes + merges)
| Node | Agent | Scope | Type | Blocked By | Deliverables |
|------|-------|-------|------|-----------|-------------|
| 10 | @backend-engineer | [integration] | write | 6, 7 | Router wiring, app entry |
| 11 | @frontend-engineer | [integration] | write | 8, 9 | Route registration, app shell |
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 · 181 lines · 49 tokens per session scan A 13b36da0dbe9
parallel-dispatch-dag is a skill published in the GitHub repository irahardianto/rugged-gemini (5 stars, last pushed 3mo ago), licensed MIT. It adds 49 tokens to every session and 1,846 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…
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…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…