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/flow)<a href="https://agentmods.dev/commands/higoralves/orc/flow"><img src="https://agentmods.dev/badge/commands/higoralves/orc/flow/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/flow"><img src="https://agentmods.dev/badge/commands/higoralves/orc/flow.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 | $0.00053 | $0.03563 |
| Opus 5.5 | $0.00021 | $0.01425 |
| Sonnet 5.5 | $0.00011 | $0.00713 |
| Haiku 4.5 | $0.00005 | $0.00356 |
Grade A, and why
flow 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 12d 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.
- Bash(curl:*) How it starts
The opening of the file, as written. The whole thing — 205 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/orc:flow
Drive a piece of work from "I want to do X" to "PR merged, workspace cleaned up." /orc:flow is the umbrella — it walks the same phases the individual commands do, but with unified state, gates at genuine decision points, and a single resume entry point.
Interactivity follows the gate taxonomy (orc:using-orc) and the resolved interaction_policy (the banner's policy: segment): real choices gate via AskUserQuestion; machine-verified outcomes (clean red, QA pass with a complete packet) print their evidence and advance; hard-outward gates always ask at every level. Immediately before each gate, print the one-line > **⛔ Gate — <phase>** callout per orc:callouts (options never go inside the callout).
Arguments
<task description>— required. One sentence describing the work.--auto[=guided|full]— autopilot level for this run (bare--auto= full). Overrides the configuredinteraction_policy. See "Autopilot" below.--type=feature|bug|refactor|docs— optional; pre-answers the triage type question. The type changes which phases run.--rfc— insert an RFC phase before planning (multi-week, multi-team, or genuine-alternatives work).--verbose— pass through to/orc:ship(long-form PR body; terseorc:caveman-pris the default).--driver playwright|agent-browser|chrome— pre-answers Phase 6's browser-driver gate.--target <name>— pre-answers Phase 6's Target gate (orc:qa-targets); recorded as atargetdecision.--explainer— pre-answers Phase 6's post-QA explainer gate with "build now".--pause-at-implement— Phase 5 pauses for the human to write the code (keeps Phase 4's red-confirm gate).--jira <KEY>— link a Jira ticket silently (validate^[A-Z][A-Z0-9_]*-\d+$); lands asResolves <KEY>in the PR body.--max-loc <N>/--no-size-gate— pass-through to/orc:ship's Phase 4.5 size gate (single owner; flow never pre-flights it).--repos a,b/--repo a/--all-repos/--this-repo— workspace-mode targeting perorc:workspace-mode.
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.
- 12d ago Changed · +2 lines d3bceb88e1a2
- 14d ago Changed · +1 lines e4e7023a9f51
- 1mo ago First seen · 202 lines · 53 tokens per session scan A feaecf1478b2
flow is a command published in the GitHub repository HigorAlves/orc (6 stars, last pushed 10d ago), licensed MIT. It adds 53 tokens to every session and 3,563 once invoked, about $0.0002 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 2026-08-31.
Other commands, from other repositories
status
A project-status command that checks a code repository and its supporting project notes. The supplied description is in Chinese and lists checks for Git, a memory bank, dependencies, environment settings, components, and conflicts.
status
Show what is known, in flight, planned and enforced across every session.
pm
A product-management command that turns a short or unclear request into a written product requirement. It uses the project's existing context to define scope, acceptance criteria, priorities, decisions, and assumptions.
task
A command for breaking work into small, trackable tasks and managing their status. It defines states such as pending, in progress, completed, and blocked.
insert-phase
Insert urgent work as decimal phase (e.g., 72.1) between existing phases.
remove-phase
Remove a future phase from roadmap and renumber subsequent phases.