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.
git clone --depth 1 https://github.com/HigorAlves/orcWrote 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/commands/higoralves/orc/fan-out)<a href="https://agentmods.dev/commands/higoralves/orc/fan-out"><img src="https://agentmods.dev/badge/commands/higoralves/orc/fan-out/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/commands/higoralves/orc/fan-out"><img src="https://agentmods.dev/badge/commands/higoralves/orc/fan-out.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 | $0.00039 | $0.01757 |
| Opus 5 | $0.00019 | $0.00879 |
| Sonnet 5 | $0.00008 | $0.00351 |
| Haiku 4.5 | $0.00004 | $0.00176 |
Grade A, and why
fan-out 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 9d 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 — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/orc:fan-out
When you have N independent tasks that can run without sharing state, fan them out instead of doing them sequentially.
When to reach for /orc:fan-out vs /orc:flow
/orc:flow— when you're driving ONE feature/bug/refactor end-to-end and the plan has parallel-safe slices in Phase 5. The umbrella handles the parallel dispatch inside the lifecycle (plan → start → parallel implementation → QA → ship)./orc:fan-out— when you have N independent things that aren't a single feature pipeline. Multi-PR review, paralleled investigations, multi-repo work, doc bulk updates, partial-plan execution without the full lifecycle. No phases, no QA, no ship — just dispatch and collect.
The two are different abstraction levels: /orc:flow is a lifecycle, /orc:fan-out is a parallelism primitive.
Arguments
--from-plan— read tasks from the current.orc/<branch>/files/plan.md(or named plan). De-emphasized path: for plans inside an active feature flow, prefer/orc:flowwhich handles parallel batches in-context with QA + ship after.--max <n>— cap concurrent agents (default 5; 8 for Sonnet-only sets).--agent <name>— explicit agent type for all tasks (e.g.--agent orc-pr-reviewerfor multi-PR review,--agent orc-debug-investigatorfor paralleled investigations). Default: auto-pick per task shape (slice → orc-implementer; otherwise general-purpose).- The remaining argument is either a freeform task list or
use plan.md.
Workflow
Phase 0 — Detect context
!orc-workspace-detect --banner
Context is injected above (ORC_* vars are exported for any Bash you run — do not re-run detection).
In workspace mode, resolve targetRepos from flags or via AskUserQuestion. The fan-out task axis becomes (slice × repo): when a plan has slices tagged repo: api and repo: ui, each slice fans out to one implementer in its own repo. When tasks are not slice-shaped (research, multi-PR review, doc updates), the axis is just per-repo.
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.
- 9d ago First seen · 98 lines · 39 tokens per session scan A 9d842f7f19e2
fan-out is a command published in the GitHub repository HigorAlves/orc (6 stars, last pushed 12d ago), licensed MIT. It adds 39 tokens to every session and 1,757 once invoked, about $0.0002 per session on Opus 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 commands, from other repositories
land
Cadence-tick autonomous PR babysitter (CI-fix, resolve, converge, merge, close, release).
sync
Manually trigger plan-sync to update downstream task specs after implementation drift.
setup
Set up Postman MCP Server. Authenticate via OAuth or API key, verify connection, select workspace.
test
Run Postman collection tests, analyze results, diagnose failures, and suggest fixes.
get-flow-run
Inspect a Postman Flow run by its Run ID — per-block logs, failing block, and status.
uninstall
Remove flow-next files from project.