Borrowing it
Nothing to install: this file belongs to fo0/clawstash. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/fo0/clawstash/main/.claude/skills/orca/SKILL.mdgit clone --depth 1 https://github.com/fo0/clawstashWrote 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/fo0/clawstash/orca)<a href="https://agentmods.dev/skills/fo0/clawstash/orca"><img src="https://agentmods.dev/badge/skills/fo0/clawstash/orca/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/fo0/clawstash/orca"><img src="https://agentmods.dev/badge/skills/fo0/clawstash/orca.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 | $0.00118 | $0.03379 |
| Opus 5.5 | $0.00047 | $0.01352 |
| Sonnet 5.5 | $0.00024 | $0.00676 |
| Haiku 4.5 | $0.00012 | $0.00338 |
Grade A, and why
orca 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 26d 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 — 181 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Orca — Orchestrator Mode
When to Use
/orca(reports state and width) ·/orca on|off|status·/orca 10— the user asks what the mode is set to, or changes it/orca <objective>·/orca <N> <objective>— an objective to carry through a delegated run, optionally at a stated width- "orca mode", "orchestrator mode", "orca an/aus", "ab jetzt delegieren", "delegate more"
- Session start, when
SCRATCHPAD.mdstill carries an Orca line from an earlier session or from before a compaction
Not this skill: choosing a subagent_type for one assignment while already orchestrating. That is the subagent_type
table in agent_docs/review_process.md → Subagent Delegation; the roles and their seats are in CLAUDE.md → Subagents.
Scope Boundaries
Owns: how work is divided across subagents and at what width — the delegation contract itself.
Does not own: when the work runs (scheduler), the stop condition checked between turns (Claude Code's built-in /goal), the review contract it delegates against (agent_docs/review_process.md).
Invocation
The text after the skill name is the argument. It arrives substituted at the bottom of this section; parse it in this order — the first match wins:
| Argument | Reading | Effect |
|---|---|---|
| (empty) | status | Report state and width, change nothing |
exactly status |
status | Report state and width, change nothing |
exactly on / off |
mode | off → plain Claude Code behavior for the rest of this session · on → back to orchestrating at the last width set |
exactly an integer N |
width | Set the parallel width for this session, change nothing else |
integer N + more text |
width + objective | Set the width, then run the rest as an objective run (below) |
| anything else | objective | An objective run at the current width |
A control word counts only as the whole argument. /orca off is the mode command; /orca off-by-one in the paginator is an objective, because "off" is not the entire string. Same for on and status. An objective that
genuinely starts with a bare control word gets rephrased, not guessed at.
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.
- 26d ago Changed · +9 lines · -46 tokens per session ed61e9e5e184
- 1mo ago Changed · +2 lines 1bf35687d650
- 1mo ago Changed · +1 lines e42394ca5602
- 1mo ago Changed · +74 lines · +44 tokens per session 086a3db4a106
- 2mo ago First seen · 95 lines · 120 tokens per session scan A 401de133f647
orca is a skill published in the GitHub repository fo0/clawstash (1 stars, last pushed today), licensed MIT. It adds 118 tokens to every session and 3,379 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 2026-08-31.
Other skills, from other repositories
@elad12390/web-research-assistant
Comprehensive MCP server for web research with 16 tools: SearXNG + Exa AI search, batch search and batch crawling, URL crawling, stealth scraping (Cloudflare bypass), package registry lookup (npm/PyPI/crates), GitHub stats, changelog fetching, tech comparison, error translation, API docs discovery, stock image search…
football-data
Look up or code against football (soccer) statistics from Football Charts, covering results with half-time scores, league tables, fixtures, goal timing and season projections for 98 leagues, including lower divisions. Use when the user asks about football results, tables or fixtures, or writes code that needs football…
local-delegation
Regla y catálogo para delegar pasos mecánicos (resumir, clasificar, extraer, boilerplate, mensaje de commit desde un diff, traducir texto o archivo, resumir salida de lint/tests/CI, explicar código, describir una imagen, verificar si el backend local está disponible) a modelos locales vía las tools local del MCP…
publish-release
Releases a new McpOrchestrator version end to end — version bump PR, tag, and the automated deploy to GitHub Releases, NuGet, and the MCP Registry. Use when asked to release, publish, deploy, ship, or bump the version of McpOrchestrator.
spotify-mcp-doctor
Diagnose and repair NovaLux12/spotify-mcp-server failures — auth, permissions, devices, rate limits, OpenClaw wiring. Use when Spotify tool calls fail or setup stalls.
internet-archive-guide
Use ia tools to investigate historical web pages or Internet Archive books and documents. Resolve capture and item identities, compare the captures actually served, and check coverage before claiming content absent or fully read.