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 Apra-Labs/apra-fleet --skill fleetgit clone --depth 1 https://github.com/Apra-Labs/apra-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/apra-labs/apra-fleet/fleet)<a href="https://agentmods.dev/skills/apra-labs/apra-fleet/fleet"><img src="https://agentmods.dev/badge/skills/apra-labs/apra-fleet/fleet/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/apra-labs/apra-fleet/fleet"><img src="https://agentmods.dev/badge/skills/apra-labs/apra-fleet/fleet.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00022 | $0.04496 |
| Opus 5.5 | $0.00009 | $0.01798 |
| Sonnet 5.5 | $0.00004 | $0.00899 |
| Haiku 4.5 | $0.00002 | $0.00450 |
Grade A, and why
fleet scanned grade A with 1 finding 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 29d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
| `'deny'` | Commands invoking network tools (curl, wget, ssh, git push, etc.) are blocked | The source is not reproduced here
A licence we could not identify
The repository carries a LICENSE file, but it is custom or dual enough that GitHub cannot name it and neither can this catalogue. Unknown terms are not permission, so the body is not copied here. Read the licence at the source and decide for yourself.
What ships with it
23 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.
- auth-azdevops.md 6.7 KB
- auth-bitbucket.md 2.2 KB
- auth-github.md 3.1 KB
- beads-conflict-resolution.md 5.7 KB
- beads.md 3.5 KB
- knowledge-agent.md 2.1 KB
- onboarding.md 4.1 KB
- permissions.md 9.2 KB
- profiles/base-dev.json 1.0 KB
- profiles/base-reviewer.json 807 B
- profiles/cpp.json 165 B
- profiles/dotnet.json 71 B
- profiles/go.json 148 B
- profiles/jvm.json 186 B
- profiles/node.json 342 B
- profiles/python.json 258 B
- profiles/rust.json 151 B
- profiles/tag-devops.json 211 B
- profiles/tag-gpu.json 186 B
- profiles/tag-kb-reconciler.json 384 B
- profiles/tpl-permissions.json 153 B
- skill-matrix.md 2.0 KB
- troubleshooting.md 2.6 KB
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.
- 29d ago Changed a90df4c3e96b
- 1mo ago Changed ba33c07b0116
- 1mo ago Changed · +2 lines 51a459793130
- 1mo ago First seen · 307 lines · 22 tokens per session scan A 033de4d2d976
fleet is a skill published in the GitHub repository Apra-Labs/apra-fleet (105 stars, last pushed today), with no licence file. It adds 22 tokens to every session and 4,496 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
create-handoff
Create a bounded handoff for another agent or person on the board with handoffsend, after confirming the recipient, the request and the sensitivity with the user.
close-handoff
Close or park a handoff with handoffupdatestatus, marking it completed or blocked as its recipient, or cancelled as its sender while it is still queued.
review-handoffs
Review the user's handoff inbox with handoffinbox and read a single handoff with its append-only event history with handoffget.
accept-handoff
Accept a queued or blocked handoff addressed to the user with handoffacknowledge, after reading it in full with handoffget.
api-errors
McpError constructor, JsonRpcErrorCode reference, and error handling patterns for @cyanheads/mcp-ts-core. Use when looking up error codes, understanding where errors should be thrown vs. caught, or using ErrorHandler.tryCatch in services.
okx-cex-trade
Use when the user asks to 'buy BTC', 'sell ETH', 'place a limit order', 'place a market order', 'cancel my order', 'amend my order', 'long BTC perp', 'short ETH swap', 'open a position', 'close a position', 'set take profit', 'limit take profit', 'immediate TP', 'set stop loss', 'self-trade prevention', 'stpMode'…