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/outlinedriven/odin-gemini-cli-extension/parallel-launchnpx skills add OutlineDriven/odin-gemini-cli-extension --skill parallel-launchgit clone --depth 1 https://github.com/OutlineDriven/odin-gemini-cli-extensionWrote 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/outlinedriven/odin-gemini-cli-extension/parallel-launch)<a href="https://agentmods.dev/skills/outlinedriven/odin-gemini-cli-extension/parallel-launch"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-gemini-cli-extension/parallel-launch.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 | $0.00049 | $0.00530 |
| Opus 5 | $0.00024 | $0.00265 |
| Sonnet 5 | $0.00010 | $0.00106 |
| Haiku 4.5 | $0.00005 | $0.00053 |
Grade A, and why
parallel-launch 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 5d 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.
This is a copy
100% identical to parallel-launch — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Parallel Launch
Decompose the given task into independent agent groups and execute them in broad parallel.
Process
-
Analyze the task and identify independent concerns that can run concurrently.
- Each concern must be self-contained: no shared mutable state, no ordering dependency.
- If concerns have dependencies, sequence the dependent batch after the independent batch completes.
- Consult delegation scenarios for parallelism decisions.
-
Design agent groups — for each independent concern:
- Assign a clear, scoped objective (one concern per agent).
- Select the appropriate agent type (Explore, Plan, general-purpose, or domain specialist).
- Define expected output format so results can be composed.
-
Launch all independent agents in a single tool call — never sequentially when parallel is possible.
-
Compose results once all agents complete:
- Merge non-conflicting outputs directly.
- For conflicting or overlapping results, reconcile and present trade-offs to the user.
- If any agent failed or returned incomplete results, report the gap and propose a targeted follow-up.
-
Review composed output — dispatch a review agent to verify:
- Completeness: All original concerns addressed, no gaps.
- Consistency: No contradictions between agent outputs.
- Accuracy: Claims are substantiated, sources checked, no hallucinated findings.
- Scope: Nothing extra built beyond what was asked.
- For implementation work, additionally verify spec compliance and code quality.
-
Report to user only after review passes.
Constraints
- Agents per batch: match the number of truly independent concerns (avoid artificial splitting).
- Each agent prompt must include full context — agents do not share memory.
- Do not launch agents for trivially sequential work (single file, single concern).
- If the task has fewer than 2 independent concerns, execute directly instead of launching agents.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 5d ago First seen · 49 lines · 49 tokens per session scan A ea79359c89e0
parallel-launch is a skill published in the GitHub repository OutlineDriven/odin-gemini-cli-extension (5 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 49 tokens to every session and 530 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to parallel-launch, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
askme
Verbalized Sampling (VS) protocol for intent exploration before planning, mode-aware. Default exhaustive runs full VS; collaborative runs tip-sharing dialogue; adversarial walks the design tree one fork at a time. Auto-detects from phrasing ("help me refine" → collaborative, "poke holes" → adversarial); override via…
design
Set visual and interaction direction for any UI surface (web, React, TUI, CLI, desktop, Qt, design-system tokens) before any UI code. Direction-first: generates 3-4 distinct directions via verbalized sampling, picks one via per-axis single-select, then derives palette, typography, spacing, motion budget. Loads when…
git-branchless
Enforce idiomatic git-branchless during planning and executing tasks — detached-HEAD-first work, in-memory rebase via git move, event-log recovery via git undo, deferred branch creation, speculative-merge git sync for base updates. Use when planning or executing multi-commit work, history rewrites, stack edits…
grill-ai-mastery
Hybrid interview that probes AI-engineering mastery by tip-vocabulary depth — entity referencing, loop closure, observability, harness improvement — not by token usage or LOC. Start collaborative (two-way tip exchange), escalate to adversarial probing when depth is lacking. Trigger when the user says "interview me on…
grill-me
Adversarial relentless interview against any plan or design until shared understanding is reached. Walk the decision tree, resolve dependencies one answer at a time, recommend a default per question. Trigger when the user says "grill me", "stress-test this", "interview me about this design", or otherwise asks for…
proof-driven
Proof-driven development. Use when implementing with formal verification using property-based testing, theorem proving, or proof tactics; zero unproven property policy enforced.