Orca is an application for running and coordinating multiple coding agents, giving each agent an isolated Git worktree while tracking their work in one place. Developers use it to run agents such as Codex, ClaudeCode, OpenCode, or Pi in parallel across desktop, mobile, local terminals, or remote servers.
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 stablyai/orca --skill orca-cligit clone --depth 1 https://github.com/stablyai/orcaWrote 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/stablyai/orca/orca-cli)<a href="https://agentmods.dev/skills/stablyai/orca/orca-cli"><img src="https://agentmods.dev/badge/skills/stablyai/orca/orca-cli/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/stablyai/orca/orca-cli"><img src="https://agentmods.dev/badge/skills/stablyai/orca/orca-cli.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk pass
- NVIDIA SkillSpector pass
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 | $0.00159 | $0.00582 |
| Opus 5.5 | $0.00064 | $0.00233 |
| Sonnet 5.5 | $0.00032 | $0.00116 |
| Haiku 4.5 | $0.00016 | $0.00058 |
Grade A, and why
orca-cli 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 23d 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.
What it actually says
Orca CLI
This discovery stub loads the version-matched guide from the Orca executable used for this session.
Resolve the CLI for this session
Choose the executable once and reuse it for every later command:
- If the
ORCA_CLI_COMMANDenvironment variable is set, use its value. Orca exports this for managed WSL sessions. - Otherwise, in a dev checkout whose session exposes
ORCA_DEV_REPO_ROOT, useorca-dev. - Otherwise, on Linux outside an Orca-managed terminal, use
orca-ide. Never run bareorcathere — outside Orca's terminals it normally resolves to the GNOME Orca screen reader (/usr/bin/orca) and starts speech on the user's machine. - Otherwise, use
orca.
Below, ORCA is a placeholder for the executable you resolved. Substitute it before
running anything; do not create a shell variable or run ORCA literally. This works the
same way in POSIX shells, PowerShell, and cmd.exe.
If the selected executable cannot run, report its exact error and stop. Do not fall through to another executable, which could silently target a different Orca build.
Load the version-matched guide before running Orca commands
ORCA skills get orca-cli
Prefer --json. Use the selected executable's --help for commands or flags the guide does
not cover. If a command reports that Orca is not running, start it with ORCA open --json
and retry. If it fails with runtime_access_denied, your sandbox blocked the connection:
re-run it with escalated permissions, and do not run ORCA open or restart Orca. If
skills get is unknown, explain that updating Orca restores the guide; use --help for
read-only discovery and do not guess unsupported commands.
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.
- 23d ago Changed · +2 lines aa76f8650501
- 1mo ago Changed · -1 lines · -4 tokens per session 6522a3355993
- 1mo ago Changed · -35 lines · -86 tokens per session b21b9b80475c
- 1mo ago Changed · +2 lines · +44 tokens per session 6dcbd69045c7
- 1mo ago First seen · 80 lines · 205 tokens per session scan A cdd5d9c8a958
orca-cli is a skill published in the GitHub repository stablyai/orca (94,483 stars, last pushed today), licensed MIT. It adds 159 tokens to every session and 582 once invoked, about $0.0006 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
integrations
Discover and call the tools a connected integration exposes, such as Linear, GitHub, Sentry, or Notion, through superset mcp. Use when the user wants something done in a connected service, asks what an integration can do or which tools it has, wants a specific tool called, asks why an integration's tools are failing…
panes
Arrange the tabs and split panes of a Superset workspace in the desktop app from an agent. Use when the user asks to split a pane, open a tab, run a command in a new pane, resize, swap, move, focus, close, or even out panes, lay out a dashboard of terminals, or show them something side by side, including "split this…
automate
Turn a recurring chore into a Superset automation. Drafts the agent prompt, confirms the schedule or event trigger and the target, creates it with the CLI, and reviews the first run together. Use when the user wants a scheduled or recurring agent, a daily or weekly job, or an agent that reacts to a Slack message…
triage-superhuman-inbox
Work through a Superhuman inbox — sort what is there into needs a reply, waiting on someone else, worth knowing, and noise, then archive, star, label, remind, or unsubscribe only as the user directs. Use when the user asks what needs their attention, what they are waiting on, to triage or clean up their inbox, or to…
find-in-superhuman
Find and read mail in Superhuman — the thread where something was said, sent, or promised — by filtering on who, when, and which split before searching by words, reading the thread before answering, and linking the thread behind every claim. Use when the user asks what someone emailed, whether a reply or an invoice…
reply-from-superhuman
Draft a reply, a follow-up, or a new email in Superhuman in the user's own voice — read the whole thread first, reuse an existing draft instead of adding a second one, keep the right people on the thread, and leave sending to the user unless they asked for it. Use when the user says reply to, answer, follow up with…