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/release)<a href="https://agentmods.dev/commands/higoralves/orc/release"><img src="https://agentmods.dev/badge/commands/higoralves/orc/release/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/release"><img src="https://agentmods.dev/badge/commands/higoralves/orc/release.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 | $0.00024 | $0.01879 |
| Opus 5.5 | $0.00010 | $0.00752 |
| Sonnet 5.5 | $0.00005 | $0.00376 |
| Haiku 4.5 | $0.00002 | $0.00188 |
Grade A, and why
release 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 — 166 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/orc:release
Cut a release from the commit history: verify the tree is releasable, compute the semver bump from conventional commits since the last tag, show the evidence, gate, then tag + gh release create. Doctrine lives in orc:release-management — invoke it (announce it) before Phase 2.
Not for orc itself
Do not run this command in orc's own repository. orc releases via the dual-tag process documented in docs/contributing.md: plugin releases use orc--v* tags (manifest bump in orc/.claude-plugin/plugin.json, tag in the last PR of a release train), and CLI releases use plain v* tags that trigger the goreleaser workflow (.github/workflows/release-cli.yml) — with a guard job that rejects cross-namespace tags. A generic single-tag release here would either misfire the CLI workflow or ship a plugin nobody can install. If the current repo is orc, stop and point the user at docs/contributing.md.
Arguments
--dry-run— stop after the preview: compute the bump, render the evidence, write nothing, tag nothing.--tag-only— skip the changelog and GitHub release; just create + push the annotated tag.
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). This command is single-repo: in workspace mode, ask which repo to release via AskUserQuestion and operate inside it. If the repo is orc itself (remote or directory name matches), stop per "Not for orc itself".
Phase 1 — Preflight: clean tree + green suite
Hard rule from orc:release-management — never release from a dirty tree or red suite.
git status --porcelain— must be empty. Untracked files count as dirty.- Detect and run the project's test command (
package.jsonscripts,Makefile,go test ./...,cargo test,pytest— whatever the repo actually uses). Read the output; perorc:verification-before-completion, no green claim without evidence. - Confirm the current branch is the release branch (normally the default branch). Releasing from a feature branch is almost always a mistake — surface and confirm before continuing.
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 · +1 lines · -14 tokens per session 8c2bdc655362
- 1mo ago First seen · 165 lines · 38 tokens per session scan A 1ec7d5a8dfe9
release is a command published in the GitHub repository HigorAlves/orc (6 stars, last pushed yesterday), licensed MIT. It adds 24 tokens to every session and 1,879 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
release
Release guide version (CHANGELOG + VERSION + README + landing sync + commit + push).
update-infos-release
Update Claude Code releases tracking (guide + landing + version bump).
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.
changelog
View recent CHANGELOG entries.
changelog-claude
Read the Claude Code changelog since the last run (plus the Claude Platform release notes for model changes), triage every entry against the global Claude Code setup, and apply the improvements the owner approves. Ledgered, so nothing is re-offered.
ship
Branch, commit, open PR, gather Claude + every enabled AI reviewer (Copilot, CodeRabbit, etc.), fix/justify/resolve every finding, loop until clean, then merge. Run only when implementation is finished AND the owner has said to ship (e.g. "ship it") — never self-invoke just because the work looks done. To design and…