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/robertsfeir/atelier-pipelineWrote 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/robertsfeir/atelier-pipeline/release)<a href="https://agentmods.dev/commands/robertsfeir/atelier-pipeline/release"><img src="https://agentmods.dev/badge/commands/robertsfeir/atelier-pipeline/release.svg" alt="Measured on agentmods" 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 | $0.00061 | $0.01990 |
| Opus 5 | $0.00030 | $0.00995 |
| Sonnet 5 | $0.00012 | $0.00398 |
| Haiku 4.5 | $0.00006 | $0.00199 |
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 8d 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 — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.
- Cutting a new versioned GitHub Release from
main - Retroactively creating GitHub Releases for already-shipped historical versions that have a CHANGELOG entry but no Release page
- Restoring/correcting an existing release's notes or
--latestmarker
Do not use /release for:
- Hot-patching production without a CHANGELOG entry — write the entry first
- Pushing tags directly to
mainwhen branch protection is on — use the version-bump-PR ceremony below - Publishing pre-release builds — those go through a different command and a different tag namespace (
vX.Y.Z-rc.N)
Eva in Release mode always works through pull requests for version-bump commits. She never pushes to main directly, even when impatient. The reason: branch-protection rules typically block direct pushes, and bypassing the PR also bypasses the release-note review that the PR description forces you to write.
Standard release ceremony
1. Pre-flight
├─ git status # working tree must be clean
├─ git switch main && git pull # local main matches origin
├─ gh pr list --state open # check for in-flight PRs that should land first
└─ Read CHANGELOG.md head # what's the proposed next version?
2. Decide version (semver)
├─ MAJOR: breaking API/CLI/schema changes
├─ MINOR: backward-compatible additions, docs milestones, license changes
└─ PATCH: bug fixes, manifest-only bumps, internal refactors
3. Version-bump branch
├─ git switch -c release/vX.Y.Z
├─ Bump every manifest with a "version" field (find them: grep -rH '"version"' --include='*.json')
├─ Add the [X.Y.Z] CHANGELOG entry — Added / Changed / Deprecated / Removed / Fixed / Security
├─ Commit: "chore(release): mybrain vX.Y.Z" (or your project's convention)
└─ git push -u origin release/vX.Y.Z
4. Open + merge PR
├─ gh pr create --base main --head release/vX.Y.Z --title "chore(release): vX.Y.Z" --body "..."
├─ Wait for CI / required reviews
└─ gh pr merge <#> --squash --delete-branch
5. Pull, capture FULL SHA
├─ git switch main && git pull
└─ git rev-parse HEAD # CRITICAL: full 40-character SHA
6. Create the GitHub Release
└─ gh release create vX.Y.Z \
--target <full-40-char-sha> \
--title "vX.Y.Z — <one-line summary>" \
--latest \
--notes "<release notes>"
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.
- 8d ago First seen · 133 lines · 61 tokens per session scan A d83b9c33e7c2
release is a command published in the GitHub repository robertsfeir/atelier-pipeline (25 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 61 tokens to every session and 1,990 once invoked, about $0.0003 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 2026-08-30.
Other commands, from other repositories
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.
release
Release a new version. Bumps version, updates docs/site/changelog, tags, pushes, and updates the marketplace repo.
release
Release the plugin — bump version across 4 files, then optionally commit, tag, push, and create a GitHub Release.
ship
Ship workflow — detect base branch, merge, run tests, review diff, bump VERSION, update CHANGELOG, commit, push, create PR.
document-release
Post-ship documentation update — reads all project docs, cross-references the diff, updates README/ARCHITECTURE/CONTRIBUTING/CLAUDE.md to match what shipped.
close-track
Close a completed track — run quality gate, update conductor state, commit, and optionally handle the git branch.