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 OutlineDriven/outline-driven-development --skill cherrypick-to-releasegit clone --depth 1 https://github.com/OutlineDriven/outline-driven-developmentWrote 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/outlinedriven/outline-driven-development/cherrypick-to-release)<a href="https://agentmods.dev/skills/outlinedriven/outline-driven-development/cherrypick-to-release"><img src="https://agentmods.dev/badge/skills/outlinedriven/outline-driven-development/cherrypick-to-release.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00041 | $0.00976 |
| Opus 5 | $0.00020 | $0.00488 |
| Sonnet 5 | $0.00008 | $0.00195 |
| Haiku 4.5 | $0.00004 | $0.00098 |
Grade A, and why
cherrypick-to-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 — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cherrypick to release
Contract
| Field | Bound contract |
|---|---|
| Trigger | User asks to cherry-pick, backport, or apply a hotfix to a release branch, providing a PR number, commit SHA, or issue reference. |
| Authority | Remote: creates cherrypick branches, pushes them, opens one PR per channel, and assigns the on-call reviewer; requires explicit human invocation. Preview the target release channel(s), the commit(s) to apply, and the PR/assignment consequence before creating branches, pushing, or opening PRs. |
| Side effect | Creates one cherrypick branch per release channel, cherry-picks and pushes the commit(s), opens one PR per channel, and assigns the on-call reviewer. No force-push, no deletion, no merge. |
| Done | A correctly titled PR with the on-call reviewer assigned exists for every requested release channel; conflicts stop for user resolution. |
Inputs
- A PR number, commit SHA, or issue reference identifying the change to apply. Required.
- The release channel(s) to target, as release branch names. Required; at least one.
- The on-call reviewer to assign. Required.
- Optional: an explicit branch-name prefix or commit subset when the reference resolves to more than one commit.
Procedure
- Resolve the supplied reference to the exact commit SHA(s) to apply. If a PR number or issue reference yields more than one commit, confirm the subset with the user before proceeding. Done when: the exact commit SHA(s) are resolved or the user confirms the subset.
- For each requested release channel, confirm its base release branch exists and is current, then fetch and check it out. Done when: every requested release branch is checked out and current, or the missing one is named.
- Preview the operation to the human: the channel(s), the commit SHA(s), the branch names that will be created, the push, the PR titles, and the on-call reviewer assignment. Proceed only after explicit human confirmation. Done when: the human confirms the operation, or the run stops for lack of confirmation.
- For each release channel, create a cherrypick branch off that channel's base branch and cherry-pick each resolved commit in source order. Done when: each commit is cherry-picked onto its cherrypick branch, or a conflict stops that channel.
- If a cherry-pick conflicts, stop that channel immediately; do not resolve, force, or skip it. Leave the working tree in the conflicted state and report it for user resolution. Done when: the conflicted channel is stopped with files and base branch named.
- Push each non-conflicted cherrypick branch to the remote. Done when: each non-conflicted branch is pushed, or the remote error is reported and the branch left intact.
- Open one PR per non-conflicted channel against that channel's base branch, titled to identify the cherry-pick and the source reference, and assign the on-call reviewer. Done when: one PR is opened and assigned per non-conflicted channel.
- Report the set of opened PRs and the set of channels stopped on conflict. Done when: every requested channel is reported as opened-with-PR or stopped-on-conflict.
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.
- 2d ago Changed 55d4c587f601
- 4d ago First seen · 45 lines · 41 tokens per session scan A 22145269d273
cherrypick-to-release is a skill published in the GitHub repository OutlineDriven/outline-driven-development (52 stars, last pushed 2d ago), licensed Apache-2.0. It adds 41 tokens to every session and 976 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
git-branchless
Use when asked for multi-commit stack edits, rebases, fixups, or stacked-PR publishing with branchless git idioms. Not for plain-git workflows in repos without branchless.
atomic-issues-prs
Use when the user says "atomic PRs" or requests one issue or PR per logical change. Don't use for single-change pushes or uncommitted change-sets.
post-merge-cleanup
Use when a landed merge, release, or completed change needs its cleanup surface reconciled. Scans for stale TODOs, deprecations, unused flags, and doc gaps. Not for unrelated refactoring.
git-workflow-and-versioning
Use when the user asks for release, version bump, changelog, or branch workflow beyond a single commit. Don't use for single commits or for publishing to a package registry.
lockstep-version-guard
Use when a human invokes the release gate to prove all 28 ODIN plugins share one canonical version. Emits a per-file comparison and exits non-zero on mismatch. Don't use to edit release metadata or for remote, credential, publish, deploy, or irreversible changes.
release-announcement
Write a release announcement — changelog, blog post, in-app note, or social post — that leads with user impact, names the audience, and includes upgrade/migration steps without filler.