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/setup)<a href="https://agentmods.dev/commands/higoralves/orc/setup"><img src="https://agentmods.dev/badge/commands/higoralves/orc/setup/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/setup"><img src="https://agentmods.dev/badge/commands/higoralves/orc/setup.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 | $0.00032 | $0.02219 |
| Opus 5.5 | $0.00013 | $0.00888 |
| Sonnet 5.5 | $0.00006 | $0.00444 |
| Haiku 4.5 | $0.00003 | $0.00222 |
Grade A, and why
setup 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 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.
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 — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/orc:setup
Scaffold the per-repo configuration that orc's tracker-aware surfaces assume:
- Issue tracker — where issues live and how to create/query them →
docs/agents/issue-tracker.md - Triage labels — the label vocabulary for the triage state machine →
docs/agents/triage-labels.md - Domain docs — where
GLOSSARY.mdand ADRs live, and the consumer rules for reading them (perorc:domain-modeling) →docs/agents/domain.md
These files are read by orc:to-issues, orc:to-prd, /orc:triage, /orc:wayfinder, and the Jira adapters (orc:jira-cli, orc:evidence-publish) — the tracker choice recorded here decides whether they call gh, acli, or write local markdown.
This is a prompt-driven interview, not a deterministic script: explore, present what you found, confirm, then write. Run once per repo. Re-run only to switch trackers or restart from scratch — day-to-day edits go straight into docs/agents/*.md.
Arguments
--tracker github|jira|local— pre-answer Section A; the interview skips the tracker question and only confirms details (project key for Jira, directory for local).
Workflow
Phase 1 — Explore (auto-settle)
Look before asking. Every fact settled here removes a question from Phase 2:
git remote -v— GitHub remote? Which repo?gh repo view --json nameWithOwner,hasIssuesEnabledandgh auth statusconfirm theghpath works.command -v acli+acli jira auth status— is the Jira CLI installed and authenticated? Only offer Jira as a recommended answer when it is.gh label list— existing label vocabulary. If labels matching the five canonical triage roles (or close variants likebug:triage) already exist, capture them as the proposed mapping instead of proposing new labels.docs/agents/— prior output of this command? Ifissue-tracker.mdexists, this is an update run: show the current choice and ask whether to keep, tweak, or restart.CLAUDE.md/AGENTS.mdat the repo root — which exists, and does either already have an## Agent skillssection?GLOSSARY.md,GLOSSARY-MAP.md,docs/adr/— existing domain-doc layout.- Monorepo signals —
pnpm-workspace.yaml, aworkspacesfield,turbo.json, populatedpackages/*with their ownsrc/. Absence means single-context, which is almost every 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.
- 2d ago Changed · +4 lines · -18 tokens per session c56444ac1e6f
- 1mo ago First seen · 120 lines · 50 tokens per session scan A b76bf4705cfd
setup is a command published in the GitHub repository HigorAlves/orc (6 stars, last pushed yesterday), licensed MIT. It adds 32 tokens to every session and 2,219 once invoked, about $0.0001 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 commands, from other repositories
scout-meta-review
Run an interactive Scout meta-review — a system-level audit that sits above the individual session types. Checks whether sessions are running, mistake audit is trending well, proposals are flowing, KB files are healthy, and data-source coverage is consistent across session types. Runs in the current conversation.
scout-work
Interactive work session — walks through today's actionable items one at a time, presents a recommended action with draft content, and executes each one only with explicit approval. Runs in the current conversation (not as a background session).
execute
Execute the next available tracked task with TDD, pre-commit validation, PR creation, AI code review, and issue tracker bridge sync.
dashboard
Compact visual progress dashboard with progress bar, task table, dependency graph, and active/blocked/next status.
standup
Show a daily standup summary with completed, in-progress, and blocked tasks across all active epics.
status
Show current execution status with progress, dependencies, file ownership, and parallelization opportunities.