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 agentmods add skills/luisfelipemoro/harness-devkit/release-managementnpx skills add LuisFelipeMoro/Harness-devkit --skill release-managementgit clone --depth 1 https://github.com/LuisFelipeMoro/Harness-devkitWrote 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/luisfelipemoro/harness-devkit/release-management)<a href="https://agentmods.dev/skills/luisfelipemoro/harness-devkit/release-management"><img src="https://agentmods.dev/badge/skills/luisfelipemoro/harness-devkit/release-management.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 | $0.00066 | $0.00490 |
| Opus 5 | $0.00033 | $0.00245 |
| Sonnet 5 | $0.00013 | $0.00098 |
| Haiku 4.5 | $0.00007 | $0.00049 |
Grade A, and why
release-management 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 5d 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.
What it actually says
The version bump follows the conventional commits since the last tag, and the GitHub release stays a draft for the human to review before publishing — nothing publishes automatically.
Not the same thing as a
release/*branch. A pipeline delivery works onrelease/{slug}-{key}and stops at opening a PR (seecoding-pipeline/references/delivery-and-worktree.md). This skill is the step after a human has merged that PR: it tags an already-mergedmainand drafts the GitHub release. Run it onmainafter the merge — never on an unmerged delivery branch, and never as a way to get delivery work ontomain.
Contract
- Input: a repository on
main, with the delivery PR already merged, and conventional-commit history since the last tag. - Output: an updated CHANGELOG.md, an annotated git tag pushed to origin, and a drafted GitHub release URL.
- Tool boundary: the draft release is never auto-published; version confirmation is requested from the user before tagging.
- Done when: the draft release URL prints for the user to review and publish.
Steps
- Determine the version bump: the git commands and the conventional-commit→semver table in
references/commands-and-templates.mdmap commits since the last tag, where the highest-priority type wins. - Compute the new
vX.Y.Zfrom the last tag, then confirm it with the user before tagging. - Update CHANGELOG.md from the Keep a Changelog template in
references/commands-and-templates.md, grouping commits by type. - Tag and push with the git commands in
references/commands-and-templates.md. - Draft the GitHub release with the
ghcommand inreferences/commands-and-templates.md, then hand the resulting URL to the user.
References
references/commands-and-templates.md— git/gh commands, the semver mapping table, and the CHANGELOG template.
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.
- 5d ago First seen · 25 lines · 66 tokens per session scan A 7a2babf45337
release-management is a skill published in the GitHub repository LuisFelipeMoro/Harness-devkit (11 stars, last pushed 4d ago), licensed MIT. It adds 66 tokens to every session and 490 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 2026-08-31.
Other skills, from other repositories
agent-release-swarm
Agent skill for release-swarm - invoke with $agent-release-swarm.
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.
release
Cut a Symphony release by bumping the committed version, landing it, tagging the merged commit, and verifying the Burrito release workflow. Use when asked to release, tag, or retag Symphony.
changelog
Create changelog files for important commits in a PR.
multi-agent-release-manager
Cleans up the workspace, formats code, runs presubmit checks, and uploads CLs to Gerrit.
refresh-arm-sdk-release
WORKFLOW SKILL — Prepares Azure.ResourceManager SDK refresh pull requests in azure-sdk-for-net. WHEN: "prepare sdk refresh", "refresh Azure.ResourceManager package", "update ARM SDK from autorest tag", "refresh changelog dependencies". INVOKES: git and GitHub pull request tools for branch, commit, push, and PR…