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 agentmods add commands/higoralves/orc/flowgit clone --depth 1 https://github.com/HigorAlves/orcWhat 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 | $0.00053 | $0.03472 |
| Opus 5 | $0.00026 | $0.01736 |
| Sonnet 5 | $0.00011 | $0.00694 |
| Haiku 4.5 | $0.00005 | $0.00347 |
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 2d 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 — 202 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 agent-browser|chrome— pre-answers Phase 6's browser-driver gate.--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.
Every flag records its answer as a settled decision (orc-state decision set … --provenance flag) so nested commands never re-ask.
Phases
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.
- 2d 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 5d ago), licensed MIT. It adds 53 tokens to every session and 3,472 once invoked, about $0.0003 per session on Opus 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
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.
refine-title
深度分析 Issue 或 PR 内容，并将其标题重构为 Conventional Commits 格式.
get-flow-run
Inspect a Postman Flow run by its Run ID — per-block logs, failing block, and status.
warden-cost
Dollar accounting — what does each active rule actually save, in money? Translates the token-measured verdict into dollars using a price table and the agent's own token-type mix, with a per-session net and a break-even. Read-only; spends no tokens.
routine
Execute one maintenance routine defined in scv/routines/ .md (task + guardrails + exit-criteria contract), or list defined routines. SCV never schedules — pair with host features like /loop or cron yourself. Use whenever the user asks to run a recurring maintenance task, or asks what routines exist — not only when…