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/code-review)<a href="https://agentmods.dev/commands/higoralves/orc/code-review"><img src="https://agentmods.dev/badge/commands/higoralves/orc/code-review/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/code-review"><img src="https://agentmods.dev/badge/commands/higoralves/orc/code-review.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 | $0.00045 | $0.04226 |
| Opus 5.5 | $0.00018 | $0.01690 |
| Sonnet 5.5 | $0.00009 | $0.00845 |
| Haiku 4.5 | $0.00005 | $0.00423 |
Grade A, and why
code-review 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 11d 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 — 277 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/orc:code-review
Review a pull request authored by someone else. Default behavior: post a real GitHub PR review with inline comments anchored to the right files and lines, optional one-click suggestion blocks, and a review event determined mechanically from finding severities.
The agents (orc-pr-reviewer, orc-security-reviewer) return structured JSON findings. This command merges them, sanity-checks for verdict-vs-severity contradictions, shows a preview, and posts via gh api (or the GitHub MCP if available).
Arguments
<pr-number-or-url>— required (unless--prsis given). Either123(current repo),org/repo#123, or a full URL.--prs a#1,b#2,...— workspace mode: review a set of linked PRs as one logical change. Each entry isrepo#pror full URL. Findings are tagged with[repo:<name>]and the merge order from the workspace plan is surfaced in the summary. Mutually exclusive with the positional<pr-number-or-url>.--context <description>— optional. Describes what the PR is supposed to accomplish, used for requirements-alignment checks.--summary-only— produce the legacy text-block markdown summary instead of posting inline. For when you want markdown to paste elsewhere or don't want to auto-post. Skips Phases 5–7.--soft-tests—test-severity findings drop to COMMENT instead of forcing REQUEST_CHANGES. Use for repos with weak test culture or PRs you explicitly want to land despite test gaps.--dry-run— runs through Phase 6 (preview) but never posts. The constructed payload is echoed as JSON for inspection. Useful for testing or for reviews you want to inspect locally before deciding.--include-nits— keepnit-severity findings (default: drop them). Bumps comment count but doesn't change the event.--audit— repo-wide security audit instead of a PR review. No PR ref required (and the diff-scoping phases are skipped). Dispatchesorc-security-reviewerin audit scope — whole working tree via Glob/Grep, the "introduced by this change" rule suspended — plus a secret-scanning step. Nothing is posted to GitHub; output is a markdown summary. See "Audit mode" below.
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.
- 11d ago Changed 1d4c59b3c022
- 1mo ago First seen · 277 lines · 45 tokens per session scan A 9b9580c9ebf3
code-review is a command published in the GitHub repository HigorAlves/orc (6 stars, last pushed 7d ago), licensed MIT. It adds 45 tokens to every session and 4,226 once invoked, about $0.0002 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
review
Review the current diff with a fresh-context agent that cannot edit.
coordination-audit
Run a pre-merge coordination audit — checks PR readiness, review state, merge queue hygiene, and local review policy before merger proceeds.
resolve-pr
Resolve PR review feedback — fetch unresolved threads, triage, dispatch resolver agents, reply + resolve via GraphQL.
audit-agents-skills
Audit quality of agents, skills, and commands in a Claude Code project.
release
Release manager for frontend and mobile. Writes App Store notes, user-facing changelog, flags stale docs and landing copy. Actions: notes | changelog | docs | sync.
worktree
Create a git worktree for isolated feature/fix work.