Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/cdskill/qalmanpx agentmods add skills/cdskill/qalma/qalma-releaseWrote 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/cdskill/qalma/qalma-release)<a href="https://agentmods.dev/skills/cdskill/qalma/qalma-release"><img src="https://agentmods.dev/badge/skills/cdskill/qalma/qalma-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 | $0.00057 | $0.01311 |
| Opus 5 | $0.00028 | $0.00656 |
| Sonnet 5 | $0.00011 | $0.00262 |
| Haiku 4.5 | $0.00006 | $0.00131 |
Grade A, and why
qalma-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 7d 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 — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Qalma Release
@qalma/editor, @qalma/skills, and @qalma/kit are published to npm under
the latest dist-tag while the public API stabilizes. The packages are
pre-1.0, but public releases use normal semver versions without prerelease
suffixes. The scripted release path bumps the minor version on every release
(0.2.0, 0.3.0, and so on).
Releases are tag-driven: a vX.Y.Z git tag pushed to main triggers GitHub
Actions, which builds, re-derives the version from the tag, and publishes all
three packages via npm's OIDC Trusted Publisher (no npm token in CI).
For the full architecture, history, and troubleshooting, read release-pipeline.md.
Cut a Release
-
Make sure
mainis clean and up to date (git status,git pull). -
If the current version is still on the historical beta line, bootstrap the first normal semver release explicitly:
pnpm nx release 0.2.0 --skip-publish --dry-run pnpm nx release 0.2.0 --skip-publish node tools/sync-changelog-doc.mjsThis one explicit version is needed because Nx's native
minorbump from0.1.0-beta.4resolves to0.1.0, while Qalma's new policy is to move to the next minor without a suffix. -
After
0.2.0, preview the next minor bump withpnpm release:dry-run. -
After
0.2.0, run the normal release command withpnpm release.For an explicit one-off version, call Nx directly so the version argument is passed before the changelog-sync command:
pnpm nx release <version> --skip-publish node tools/sync-changelog-doc.mjsThese scripts or commands run
nx release ... --skip-publish, then sync the generated editor changelog into the docs changelog. The release portion:- Runs the
preVersionCommand(./node_modules/.bin/nx run-many -t build -p editor skills ui-kit). - Writes the new version into
libs/editor/package.jsonanddist/libs/editor/package.json,libs/skills/package.jsonanddist/libs/skills/package.json, pluslibs/ui-kit/package.jsonanddist/libs/ui-kit/package.json. - Generates project changelogs from conventional commits.
- Commits the manifest and changelog change as
chore(release): publish <version>. - Creates an annotated tag
v<version>on that commit. - Skips publishing (CI does that).
- Runs the
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.
- 7d ago First seen · 105 lines · 57 tokens per session scan A d4ca860d382a
qalma-release is a skill published in the GitHub repository cdskill/qalma (10 stars, last pushed 1mo ago), licensed MIT. It adds 57 tokens to every session and 1,311 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
create-draft-pr
Create a draft pull request for the current session. Use when the user wants to open a draft PR with the session's changes.
create-pr
Create a pull request for the current session. Use when the user wants to open a PR with the session's changes.
release-version
Steps to cut a VNote version release (e.g. v4.3.0) — bump the version with scripts/updateversion.py, refresh and fill zhCN/ja translations via lupdate, write the changes.md changelog, and trigger the CI [Release] build. Use when asked to "release", "cut a release", "bump the version", or "prepare vX.Y.Z".
releasing-weaverse-sdks
Use when releasing @weaverse/ npm packages, bumping SDK versions, publishing to npm, or shipping the Weaverse SDKs. Triggers on "release sdk", "release weaverse", "publish packages", "release core", "release schema", "bump sdk version", "ship sdks".
shipping-and-launch
Pre-deploy hygiene for a Spring Boot 4 feature — verify gates, capture rollback plan, sign off observability, generate release notes, and stage the rollout. Used by /ship after /review approves the diff. The agent never deploys; it produces the plan a human executes.
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.