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/address)<a href="https://agentmods.dev/commands/higoralves/orc/address"><img src="https://agentmods.dev/badge/commands/higoralves/orc/address/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/address"><img src="https://agentmods.dev/badge/commands/higoralves/orc/address.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 | $0.00026 | $0.01852 |
| Opus 5.5 | $0.00010 | $0.00741 |
| Sonnet 5.5 | $0.00005 | $0.00370 |
| Haiku 4.5 | $0.00003 | $0.00185 |
Grade A, and why
address 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 14d 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 — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/orc:address
Address the reviewer feedback on your own PR. Closes the loop: code fixes + thread replies + push.
Arguments
-
--auto[=guided|full]— autopilot level for this run (overridesinteraction_policy); ladder and hard-outward exemption inorc:gates§6. -
<pr-number>— optional. If omitted, the command usesgh pr list --head $(git branch --show-current)to find the PR for the current branch.
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, identify the active workspace session and resolve the PR set:
orc-state get --field linkedPRsfor the active branch's session (read-for-data perorc:state-protocol; when an explicit<pr-number>is given,orc-state sessionsrows locate the session whoselinkedPRsincludes it).- The default address target is every URL in
linkedPRs(broadcast across all linked PRs of the workspace flow). --repo <name>narrows to one repo's PR;--repos a,bnarrows to a subset. Iron rule: no silent broadcast — when no flag is given andlinkedPRshas 2+ entries, prompt viaAskUserQuestion: "Address comments on all N PRs / pick a subset / just one PR / cancel."
When run from inside a workspace-member repo (cwd is one of the children), follow the workspace-link.json back-pointer up to the workspace registry and proceed.
Phase 1 — Fetch the PR(s) + unresolved comments
gh pr view <ref> --json number,title,headRefName,url,reviewThreads
gh api repos/{owner}/{repo}/pulls/{n}/comments --paginate
In workspace mode, run both calls per target PR in parallel and bucket comments by repo (each comment carries the PR's repo name as its origin tag).
Also fetch check state per target PR: gh pr checks <ref>. Any failing check → flag the PR as red-CI for Phase 3 (the fix batch will fold in CI fixes alongside the review fixes).
Filter to comments where the thread is unresolved. (If the reviewThreads JSON includes a isResolved: false flag, use it; otherwise treat all comments as unresolved unless the user says otherwise.)
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.
- 14d ago Changed 0d6bbd8821c9
- 1mo ago First seen · 125 lines · 26 tokens per session scan A 01a990917ad9
address is a command published in the GitHub repository HigorAlves/orc (6 stars, last pushed 10d ago), licensed MIT. It adds 26 tokens to every session and 1,852 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
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.
worktree
Create a git worktree for isolated feature/fix work.
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.