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 upex-galaxy/agentic-qa-boilerplate --skill orca-orchestrationgit clone --depth 1 https://github.com/upex-galaxy/agentic-qa-boilerplateWrote 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/upex-galaxy/agentic-qa-boilerplate/orca-orchestration)<a href="https://agentmods.dev/skills/upex-galaxy/agentic-qa-boilerplate/orca-orchestration"><img src="https://agentmods.dev/badge/skills/upex-galaxy/agentic-qa-boilerplate/orca-orchestration/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/upex-galaxy/agentic-qa-boilerplate/orca-orchestration"><img src="https://agentmods.dev/badge/skills/upex-galaxy/agentic-qa-boilerplate/orca-orchestration.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 | $0.00424 | $0.09338 |
| Opus 5.5 | $0.00170 | $0.03735 |
| Sonnet 5.5 | $0.00085 | $0.01868 |
| Haiku 4.5 | $0.00042 | $0.00934 |
Grade A, and why
orca-orchestration 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 5d 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.
- DO verify credentials on the worker's own screen before dispatching work to it. The native launch has no argv: every MCP server, on any harness, reads the worktree's own `.env` through the `.env` loader in the MCP conf How it starts
The opening of the file, as written. The whole thing — 294 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Orca Orchestration — One Conductor, a Fleet of Sessions
This skill is the transport layer for work that does not fit in one session. A conductor talks to the owner and coordinates workers; each worker is a persistent agent session that owns a scope from start to finish, reports through a mailbox, and can be interrupted, questioned and resumed. The fleet is all workers of one Run.
It is optional by construction. Everything here has a path that works with no runtime at all: the same launch lines, pasted into terminals by a human, and the same tokens and artifacts the workflow skills already write. What the runtime buys is the step a human would otherwise do with their hands, plus a mailbox instead of screen-scraping.
Read full SKILL.md when: starting a fleet cold, arbitrating a claim, choosing a topology, recovering a Run from a previous session, or writing an unattended automation.
When to use
- The user asks to parallelize, orchestrate, or run "one session per story / module / failure cluster".
- The user wants to talk to, steer, interrupt, question or close a session that is already running.
- The user wants the state of a fleet, or to pick up a wave from a previous session.
- A brief names this skill (WORKER mode).
- An unattended routine has to dispatch work with nobody at the wheel.
When NOT to use
| Situation | Use instead |
|---|---|
| a read, a verification, a map — anything that fits in this turn | one-shot subagents (AGENTS.md §3). This is most work |
| "hand this TASK to another agent and forget it" | that is a HANDOFF, not orchestration: no Task, no Dispatch, no mailbox. Ask the binary for its orca-cli guide |
| "hand this whole SESSION to a fresh one, my context is full" | ownership transfer of the session itself, same worktree, same harness |
| per-ticket manual QA | /sprint-testing |
| writing test code | /test-automation |
branch / commit / push / PR mechanics, or a plain git worktree with no fleet |
/git-flow-master |
| one long task, one session, no siblings | just do the task |
What ships with it
19 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.
- references/automations.md 12 KB
- references/brief-template.md 10 KB
- references/channel-discipline.md 7.4 KB
- references/claims-protocol.md 9.8 KB
- references/coordinator-playbook.md 30 KB
- references/gotchas.md 38 KB
- references/html-surfaces.md 4.1 KB
- references/launch-seam.md 13 KB
- references/orca-machine-setup.md 10 KB
- references/provisioning.md 11 KB
- references/session-identity.md 10 KB
- references/standby-report-contract.md 4.8 KB
- references/topologies.md 7.0 KB
- references/worker-contract.md 13 KB
- templates/COMMON.md 8.5 KB
- templates/launch.txt 5.1 KB
- templates/roster.md 2.1 KB
- templates/run.md 2.4 KB
- templates/W-brief.md 4.8 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.
- 5d ago Changed 62ddc99de9f7
- 11d ago Changed 6a6dcc0bf4da
- 12d ago Changed · -8 lines eab7cfb825d1
- 14d ago Changed · +2 lines 172dd1ff3951
- 21d ago Changed dff933d8a0f0
- 22d ago Changed 6c1d4ee888ac
- 23d ago Changed · +2 lines f44d95d7b33e
- 24d ago Changed · +18 lines 22f6f56505f1
- 28d ago Changed · +10 lines 4dfc7f149964
- 29d ago First seen · 270 lines · 424 tokens per session scan A 5cb7d1f8d65c
orca-orchestration is a skill published in the GitHub repository upex-galaxy/agentic-qa-boilerplate (26 stars, last pushed 4d ago), licensed MIT. It adds 424 tokens to every session and 9,338 once invoked, about $0.0017 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 2026-09-18.
Other skills, from other repositories
discover-product
Run a multi-round discovery (persona / pain / JTBD / scenario / MVP / assumptions) and write DISCOVERY.md.
accept-milestone
Use ONLY when the user explicitly types $accept-milestone . Do not trigger implicitly from generic phrasing.
onboarding-checklist
Create comprehensive onboarding plans that set new hires up for success. Use this skill when preparing for new employee arrivals, improving onboarding processes, or building role-specific onboarding. Activate when: onboarding, new hire, first day, new employee, orientation, employee onboarding, 30-60-90.
on-call-best-practices
Manage on-call rotations with sustainable practices, fair scheduling, and effective handoffs. Use this skill when setting up on-call, improving on-call experience, or managing rotations. Activate when: on-call, pagerduty, rotation, schedule, handoff, on-call burden, being paged, night pages, weekend on-call, on-call…
standup
(forwward) Writes outcome-first status updates leaders actually read, with options + lean recommendation for blockers. Use when the user says "standup", "status report", "progress update", "weekly update", "executive summary", "update on [project]", or pastes project details without specifying intent. Reads git log…
meeting
(forwward) Turns transcripts, rough notes, or voice memos into a clean summary with decisions, action items (owner + deadline), and open questions. Use when the user pastes unstructured notes or asks "summarize this meeting", "meeting notes", "what were the action items", "write up from this call", "debrief", "what…