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 skills add gustavo-meilus/superpipelines --skill cutting-a-releasegit clone --depth 1 https://github.com/gustavo-meilus/superpipelinesWrote 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/skills/gustavo-meilus/superpipelines/cutting-a-release)<a href="https://agentmods.dev/skills/gustavo-meilus/superpipelines/cutting-a-release"><img src="https://agentmods.dev/badge/skills/gustavo-meilus/superpipelines/cutting-a-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/skills/gustavo-meilus/superpipelines/cutting-a-release"><img src="https://agentmods.dev/badge/skills/gustavo-meilus/superpipelines/cutting-a-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 | $0.00089 | $0.01042 |
| Opus 5 | $0.00044 | $0.00521 |
| Sonnet 5 | $0.00018 | $0.00208 |
| Haiku 4.5 | $0.00009 | $0.00104 |
Grade A, and why
cutting-a-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 12d 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 — 38 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cutting a Superpipelines Release
Cut a version release after the feature PR(s) are merged into main. Full step detail + gotchas live in RUNBOOK.md — read it before acting.
Hard constraints (read first)
mainis branch-protected. No directgit push origin main. Every change goes through a PR.gh pr merge <n> --squash --adminbypassesREVIEW_REQUIRED(CI must still be green) — confirm with the user before any--adminoverride.- JSON must be BOM-free. Never
Set-Content -Encoding UTF8for JSON. Use the Edit tool orpython3writes (encoding="utf-8"). - 5 version targets must agree before tagging:
package.json,.Codex-plugin/plugin.json,.Codex-plugin/marketplace.json(plugins.0.version— NOT the top-level1.0.0),.cursor-plugin/plugin.json,AGENTS.md(- **Project Version**: vX.Y.Z). First 3 listed in.version-bump.json; last 2 are manual. - Tag ↔ changelog convention: every tag
vX.Y.ZMUST have a matching## X.Y.ZCHANGELOG entry and a## vX.Y.ZRELEASE-NOTES entry beforegh release create. - gh CLI in Bash tool: never
--body @'...'@(PowerShell here-string, fails). Write the body to a temp.md, use--body-file, thenrmit. Keep temp files out of commits.
Workflow
- Preflight —
git fetch origin; confirmorigin/mainhas the feature merge; verify all 5 version targets agree and equal the intended vX.Y.Z (npm run check:versionscovers 6 including.codex-plugin); check tag/release naming convention (vX.Y.Z — <Title Case Name>). Profile-drift check: confirm the latest "Profile drift review" issue (opened monthly by.github/workflows/profile-drift.yml) is closed or its findings are consciously deferred in the release notes; amodel_tiers_versionolder than 90 days blocks unless deferred. - Sync local main —
ExitWorktree action:keepif in a worktree;git checkout main && git pull --ff-only origin main(clear stale untracked blockers first — diff againstorigin/main). - Draft doc entries — add
## X.Y.ZtoCHANGELOG.mdand a<release_entry>toRELEASE-NOTES.md, mirroring the previous entry's format exactly. Source bullets from real changes; do not invent. - Land docs via PR — branch
release-notes-X.Y.Z, commit, push,gh pr create(--body-file), wait for CI pass, confirm intent,gh pr merge --squash --admin --delete-branch, re-sync main. - Create release + tag — extract the new CHANGELOG section as the release body, append the install line,
gh release create vX.Y.Z --target main --title "vX.Y.Z — <Title>" --notes-file <tmp>. - Verify — tag commit ==
origin/main; release not draft/prerelease;Closes #Nissues CLOSED; follow-up issues still OPEN. - Aiboarding pointer (optional) — if release docs don't touch the 3 AIBOARDING sections, no-op advance
last_synced_committo HEAD via the same PR +--adminflow. Expect one residual drift nag on the bump commit — STOP, do not chase.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 12d ago First seen · 38 lines · 89 tokens per session scan A a9f45edcbb5a
cutting-a-release is a skill published in the GitHub repository gustavo-meilus/superpipelines (4 stars, last pushed 1mo ago), licensed MIT. It adds 89 tokens to every session and 1,042 once invoked, about $0.0004 per session on Opus 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 skills, from other repositories
PR Description Writer
Writes clear, thorough pull request descriptions from a diff or list of changes.
agent-swarm-pr
Agent skill for swarm-pr - invoke with $agent-swarm-pr.
agent-pr-manager
Agent skill for pr-manager - invoke with $agent-pr-manager.
github-automation
GitHub workflow automation, PR management, issue tracking, and code review coordination. Integrates with GitHub Actions and repository management. Use when: PR creation, code review, issue management, release automation, workflow setup. Skip when: local-only changes, non-GitHub repositories.
hunk-launch-video
Produces Hunk videos by driving the real TUI headlessly in a PTY, compositing captioned 1080p frames in Chromium, and encoding with ffmpeg. Use for feature demos, workflow explainers, announcements, launch videos, and full-release roundups.
revdiff
Review diffs, files, and documents with inline annotations in a TUI overlay, or answer questions about revdiff usage, configuration, themes, and keybindings. Opens revdiff in agterm/tmux/zellij/herdr/kitty/wezterm/cmux/ghostty/iterm2/emacs-vterm, captures annotations, and addresses them. Works in git, hg, and jj repos…