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 drvoss/everything-copilot-cli --skill fleet-parallelgit clone --depth 1 https://github.com/drvoss/everything-copilot-cliWrote 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/drvoss/everything-copilot-cli/fleet-parallel)<a href="https://agentmods.dev/skills/drvoss/everything-copilot-cli/fleet-parallel"><img src="https://agentmods.dev/badge/skills/drvoss/everything-copilot-cli/fleet-parallel/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/drvoss/everything-copilot-cli/fleet-parallel"><img src="https://agentmods.dev/badge/skills/drvoss/everything-copilot-cli/fleet-parallel.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 264 Skill allows unbounded resource consumption (API calls, storage, compute). Without rate limits or quotas, a compromised or misbehaving agent can cause denial-of-service or cost overruns.Fix: Set explicit rate limits, timeouts, and resource quotas for API calls, file operations, and compute. Implement circuit breakers for runaway loops.
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 | $0.00046 | $0.03347 |
| Opus 5.5 | $0.00018 | $0.01339 |
| Sonnet 5.5 | $0.00009 | $0.00669 |
| Haiku 4.5 | $0.00005 | $0.00335 |
Grade A, and why
fleet-parallel 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 1mo 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 — 328 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Fleet Mode Parallel Execution
Why This is Copilot-Exclusive
Copilot CLI's Fleet mode launches multiple autonomous agents in parallel, each working on an independent subtask in its own context window. This is a fundamentally different execution model — not just "run commands in parallel" but full AI agents running concurrently with their own tool access. Those subagents are also steerable: if an in-flight agent starts drifting, you can send a follow-up message to correct course instead of waiting for the whole run to finish.
When to Use
- Refactoring the same pattern across many files simultaneously
- Reviewing multiple PRs or issues in parallel
- Running independent code generation tasks (tests, docs, migrations)
- Batch-processing items where each item needs AI reasoning, not just scripting
- Any task that decomposes into 3+ independent units of work
When NOT to Use
| Instead of fleet-parallel | Use |
|---|---|
| A single-file or single-function change | Work directly in the current session |
| A task with ordered dependencies between steps | Plan the sequence and run it serially |
| Subtasks that would edit the same file, lockfile, or generated artifact | Split ownership first or avoid fleet mode |
| A tiny batch of 2-3 trivial items | Handle them sequentially unless agent overhead is clearly worth it |
Write-Scope Conflict Guard
Before launching any fleet batch, validate that no two agents share write scope:
Rule: Same file = sequential. Different files = parallel.
- List all files each subtask will modify
- If two tasks name the same file, one must wait — do not launch them in the same batch
- Lockfiles, generated files, and shared config are treated the same as source files
- If scope overlap is discovered mid-run, stop the later agent, let the earlier one finish, then requeue
Workflow
1. Use the /fleet Slash Command (Recommended)
The simplest way to trigger fleet mode is the /fleet command:
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.
- 1mo ago First seen · 328 lines · 46 tokens per session scan A 18569b35b2ab
fleet-parallel is a skill published in the GitHub repository drvoss/everything-copilot-cli (47 stars, last pushed 24d ago), licensed MIT. It adds 46 tokens to every session and 3,347 once invoked, about $0.0002 per session on Opus 5.5. 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
windbg-user-heap-corruption-investigation
Use when an app, service, or user-mode driver host heap fails or Application Verifier detects corruption; inspect history and bounds. Not for kernel pool corruption or ordinary OOM.
git-tidy
Git repository triage across branches, worktrees, stashes, remote refs, tags, remotes, artifacts, ignored-but-tracked files, large blobs, and maintenance. Correlates exact work for work-bearing carriers, runs protected read-only inventory for legacy scopes, reports coverage gaps, and recommends outcomes without…
create-skill
WORKFLOW SKILL - Create and register a complete portable agent skill in a managed skills-repo.config.json repository or an existing skills repository. Produces focused instructions, documentation, deterministic tests, Vally evals, locked tooling, registration, and optional validated thumbnail art. USE FOR…
speckit-init
Scaffold a Spec Kit (spec-driven development) project for GitHub Copilot by running specify init --integration copilot --integration-options="--skills". USE FOR: starting a new spec-kit project, bootstrapping spec-driven development in an existing repo, installing spec-kit templates/scripts/commands for Copilot. DO…
create-skills-repo
WORKFLOW SKILL - Create or safely maintain a portable skills marketplace repository for multiple AI coding agents. INVOKES: bundled Node.js generator, standalone create-skill, standalone create-gh-pages-site, Vally, git, and gh. USE FOR: create a skills repo, scaffold an agent skills marketplace, upgrade a skills…
speckit-self
Check for and apply Spec Kit CLI updates via specify self. USE FOR: checking whether a newer specify-cli release is available, previewing an upgrade with --dry-run, upgrading the CLI in place (optionally to a pinned tag). DO NOT USE FOR: checking project tools/integrations (use speckit-check) or managing…