orca

Solid

Use when Pi bash/write/edit/read/discovery tool calls are protected by Orca runtime guardrails, or when secrets were captured from a Pi prompt.

AI & Automation 33 stars 2 forks Updated today Apache-2.0

Install

View on GitHub

Quality Score: 82/100

Stars 20%
51
Recency 20%
100
Frontmatter 20%
70
Documentation 15%
100
Issue Health 10%
50
License 10%
100
Description 5%
100

Skill Content

# Orca Guardrails For Pi Orca evaluates Pi tools before they run: | Tool | Path | |------|------| | `bash` | daemon Evaluate (`orca evaluate --json --stdin`, `source.host=pi`) | | `write` / `edit` | Zig `orca decide file` with `operation: write` | | `read` | Zig `orca decide file` with `operation: read` | | `grep` / `find` / `ls` | Root preflight plus explicit approval; descendants are not individually evaluated | | Any other tool name (custom / MCP-shaped) | Zig `orca decide tool` with `{"name":"<toolName>"}` (name only) | Custom/MCP-shaped tools are **name-gated** via `decide tool` — this is **not** full MCP protocol mediation or an MCP proxy. Treat an Orca block as a security decision, not as a formatting problem to route around. `grep`, `find`, and `ls` remain approval-gated even when the root preflight allows them. Do not describe a broad root check as proof that every traversed file is safe. **Process-level env/network/secretless** are **not** provided by the extension alone. Launch Pi under Orca: ```bash orca run -- pi orca run --secretless --network ask -- pi ``` Install: `pi install npm:@orca-sec/pi-orca`. Do not mix that with `pi install ./orca-pi`. When Orca blocks a command or file action: - Explain the block reason to the user without restating sensitive command or path contents. - Surface the **rule id** when present (decision cards include `rule …`). - Ask the user how they want to proceed. - Do not bypass Orca by obfuscating, splitting, encoding, rewr...

Details

Author
christopherkarani
Repository
christopherkarani/Orca
Created
2 months ago
Last Updated
today
Language
Zig
License
Apache-2.0

Similar Skills

Semantically similar based on skill content — not just same category

AI & Automation Featured

orca-cli

Use the public `orca` CLI to operate Orca-managed worktrees, folder contexts, terminals, repos, automations, worktree comments, and the browser embedded inside the Orca app. Use when the user says "$orca-cli", "use orca cli", "Orca worktree", "child worktree", "cardStatus", "spawn codex/claude in a worktree", "read/wait/send Orca terminal", "terminal send", "full handoff", "handover", "give this to another agent", "another worktree", "Orca browser", or "control the browser inside Orca". Prefer this over raw `git worktree`, ad hoc PTYs, Playwright, or Computer Use when the task touches Orca-managed state. Use Computer Use for browser windows, webviews, or desktop UI outside Orca's embedded browser.

31,265 Updated today
stablyai
AI & Automation Featured

orchestration

Use Orca orchestration for structured multi-agent coordination: threaded messages, blocking ask/reply flows, task dispatch, worker_done/escalation waits, task DAGs, decision gates, coordinator loops, or decomposing work across agents. Use `orca-cli` instead for full ownership handoffs, including requests phrased as "hand off", "handoff", "handover", "give this to another agent", or "another worktree" when the user did not explicitly ask to supervise, monitor, wait for results, or coordinate a DAG. Use `orca-cli` for ordinary terminal control, lightweight terminal prompts, shell commands, Orca worktree management, reading or waiting on terminals, and automation of the browser embedded inside Orca. Use Computer Use for browser windows, webviews, Orca app UI, or desktop UI outside Orca's embedded browser.

31,265 Updated today
stablyai
AI & Automation Listed

orca

Triggered by the slash command "/orca path/to/plan.md". Takes a finalized project plan and executes it in parallel: splits it into independent task chunks, spawns coding agents in cmux panes (default 2 per wave, hard ceiling 4 — both constants live in SKILL-lib.sh; every wave size is confirmed by the user before spawning; each agent works in its own git worktree and branch), monitors progress via status.md, rebases each completed branch onto the default branch, fast-forwards it with --ff-only, auto-resolves simple conflicts, escalates complex ones to the user, and cleans up worktrees and branches once every wave is integrated. Use this skill whenever the user runs "/orca", or asks to "execute the plan," "run the plan in parallel," "spawn agents on this," "kick off multi-agent execution," "parallelize the build," or otherwise wants a finalized plan carried out using multiple coordinated coding agents.

1 Updated 1 weeks ago
orassayag