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 brizzai/fleet --skill skillgit clone --depth 1 https://github.com/brizzai/fleetWrote 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/brizzai/fleet/skill)<a href="https://agentmods.dev/skills/brizzai/fleet/skill"><img src="https://agentmods.dev/badge/skills/brizzai/fleet/skill/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/brizzai/fleet/skill"><img src="https://agentmods.dev/badge/skills/brizzai/fleet/skill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
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 →
- high Excessive Agency · line 78 Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.Fix: Remove the model/provider override or disclose it prominently and require explicit operator approval before invoking an external coding CLI or billed model.
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 | $0.00133 | $0.02697 |
| Opus 5.5 | $0.00053 | $0.01079 |
| Sonnet 5.5 | $0.00027 | $0.00539 |
| Haiku 4.5 | $0.00013 | $0.00270 |
Grade A, and why
fleet 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 9d 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 — 217 lines — stays where its author put it; the contents beside it link to each section on GitHub.
fleet
fleet runs coding-agent sessions in parallel, each in its own tmux session and — unless
you point it at an existing directory — its own git worktree. From a shell you can create
one, hand it a task, see what it and every other session is doing, answer its prompts, and
collect its result.
Run fleet <command> --help for the exact flags. This file covers when and how to reach
for them.
When to hand work to a session
Spawn a session when the work is independent of the current turn and would otherwise block it: a second feature, a long refactor, a flaky-test hunt, an issue that just needs doing. The session gets its own worktree, so it can't collide with the tree you're editing.
Do the work inline instead when it's part of what the user asked for right now, or when it touches files being edited in this conversation.
Say which session you started and what you gave it. The user drives fleet's TUI and needs to know a new row appeared.
Start a session on a task
fleet wt <branch> -p "<the task, phrased as you would to another agent>"
Creates the worktree, starts the agent, and delivers the prompt as its first message, so
the session opens already working on it. -p accepts multi-line text and text starting
with -.
Pipe a task in from another tool with -p -, which reads stdin:
gh issue view 242 | fleet wt fix-242 -p -
Worth knowing:
--base <branch>branches from something other than the repo's default branch.--path <repo>picks the repo (defaults to cwd). It resolves to the repo's main worktree, so running it from inside one worktree doesn't nest names.--agent claude|codex|opencode|copilotoverrides the user's configured default agent.--account <email>picks which Claude subscription the session bills to. Claude only — passing it with another agent is an error, not a silent no-op.--ticket BRZ-3182materializes a Linear issue (description, comments, screenshots) into the worktree and names the branch from it. Conflicts with-p.--no-sessionmakes only the worktree and prints its path, so it composes:cd "$(fleet worktree scratch --no-session)".--model/--effort— see below.
What ships with it
2 files 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.
- 9d ago Changed · +76 lines · +29 tokens per session 148a99d17b80
- 25d ago Changed · +3 tokens per session 51db567427bf
- 2mo ago First seen · 141 lines · 101 tokens per session scan A 9c939de582b8
fleet is a skill published in the GitHub repository brizzai/fleet (59 stars, last pushed 9d ago), licensed Apache-2.0. It adds 133 tokens to every session and 2,697 once invoked, about $0.0005 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
merge-batch
Prepare and merge an owner-selected PR batch with contributor credit and exact-candidate admission. Use for a pasted PR list; combined focused validation is diagnostic, and every actual landing still requires its applicable checks and authorization.
prowler-commit
Creates professional git commits following conventional-commits format. Trigger: When creating commits, after completing code changes, when user asks to commit.
gh-auth-isolation
Safely manage multiple GitHub identities (EMU + personal) in agent workflows.
comet-github
A routing guide for Comet-related GitHub work. It directs requests about pull requests, issues, CI failures, ideas, and fixes to the appropriate review or implementation process.
github-skill
Work with GitHub via the gh CLI — clone repositories, create/list/merge pull requests, create/list issues, and run any other gh command (API calls, workflow runs, releases, repo administration). List operations return parsed JSON.
release-helper
Ensures configuration and code changes are released correctly. Use PROACTIVELY whenever you edit config.json, change any setting, or fix a configuration bug in this project, so the change reaches production.