Helmor is a local workbench for running and coordinating multiple coding agents, with each task isolated in its own Git workspace. Developers use it to review changes, test code, resolve conflicts, and merge or create pull requests. Its catalogue entries extend Helmor with skills, instructions, settings, and hooks.
Borrowing it
Nothing to install: this file belongs to dohooo/helmor. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/dohooo/helmor/main/.agents/skills/helmor-release/SKILL.mdgit clone --depth 1 https://github.com/dohooo/helmorWrote 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/dohooo/helmor/helmor-release)<a href="https://agentmods.dev/skills/dohooo/helmor/helmor-release"><img src="https://agentmods.dev/badge/skills/dohooo/helmor/helmor-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/dohooo/helmor/helmor-release"><img src="https://agentmods.dev/badge/skills/dohooo/helmor/helmor-release.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 20 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 37 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00110 | $0.02387 |
| Opus 5.5 | $0.00044 | $0.00955 |
| Sonnet 5.5 | $0.00022 | $0.00477 |
| Haiku 4.5 | $0.00011 | $0.00239 |
Grade A, and why
helmor-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 1mo 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 — 263 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Helmor Release
Use this skill to turn a branch's real changes into release metadata for Helmor:
- a clean
.changeset/*.mdentry - a pending
.announcements/*.jsonfragment when the change deserves an in-app "New in vX" toast
Workflow
-
Inspect the branch before asking the user anything.
-
Run
scripts/collect_release_context.pyto gather:- commits since the base branch
- changed files grouped by area
- a short suggested summary
-
Draft the full changeset yourself, without asking the user upfront. Decide:
- the bump (
patch/minor/major) using the Versioning Guidance below - the body shape — one prose sentence when one sentence is genuinely enough, or summary line + bullets when there are multiple distinct user-visible changes (see Default Changeset Format)
- the actual prose / bullets
Prefer a conservative bump (
patchunless there is a clear new user-visible capability). If you genuinely cannot decide the bump from the diff alone, default topatchand flag it in the confirmation step.Brevity bias. Aim for the shortest sentence that names the user-visible change — if a clause can be dropped without losing meaning, drop it. Reserve summary+bullets for releases with ≥2 distinct user-visible items.
- the bump (
-
Write the changeset to a single file under
.changeset/right away. Do not wait for approval before creating the file — the user will adjust from a real draft, not a hypothetical one. -
Decide whether an in-app release announcement is warranted.
- Create one pending file under
.announcements/only for new user-visible features or workflow changes. - Skip bug fixes, internal refactors, routine performance work, and release plumbing unless users need to learn a new behavior.
- Do not write an id or version.
bun run release:versionconsumes all pending announcement files and merges them into one catalog entry for the final version.
- Create one pending file under
-
Then, and only then, show the user what you created and offer the adjustment menu described in "Confirmation Style".
What ships with it
2 files 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.
- 1mo ago First seen · 263 lines · 110 tokens per session scan A d14048177e5e
helmor-release is a skill published in the GitHub repository dohooo/helmor (1,309 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 110 tokens to every session and 2,387 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
release
Publish a herdr-gpui release. Use when the user asks to cut, push, ship, or publish a release, or to approve, verify, or GPG-sign one that is already running. Covers just release, the protected environments the run stops at, and the local verification and signing steps that are not part of CI.
release-pr-quality-gate
Build an AgentWorks release or pull-request browser quality gate over saved suites and exact build identity. Use when a merge, deployment, or promotion needs an auditable QA decision.
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.
codew-release-qa-sweep
Use before claiming Codewhale release work is done: run the full gate sweep and list the manual QA targets.
gh-credit-harvest
Harvest one community PR into a release branch with authorship and credit preserved, verified green, and a warm thank-you.
github
Skill "github" from Hmbown/Codewhale, covering github, when to use, setup, workflow and non-goals.