Borrowing it
Nothing to install: this file belongs to zenml-io/kitaru. 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/zenml-io/kitaru/develop/.agents/skills/kitaru-release/SKILL.mdgit clone --depth 1 https://github.com/zenml-io/kitaruWrote 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/zenml-io/kitaru/kitaru-release)<a href="https://agentmods.dev/skills/zenml-io/kitaru/kitaru-release"><img src="https://agentmods.dev/badge/skills/zenml-io/kitaru/kitaru-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/zenml-io/kitaru/kitaru-release"><img src="https://agentmods.dev/badge/skills/zenml-io/kitaru/kitaru-release.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 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 Agent Snooping · line 15 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Agent Snooping · line 15 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Agent Snooping · line 353 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 | $0.00083 | $0.05867 |
| Opus 5 | $0.00042 | $0.02933 |
| Sonnet 5 | $0.00017 | $0.01173 |
| Haiku 4.5 | $0.00008 | $0.00587 |
Grade A, and why
kitaru-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 today.
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 — 394 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Release Kitaru
Use the current workflows as the source of truth:
- Core:
.github/workflows/release.yml - Plugins:
.github/workflows/release-plugins.yml - Python package inventory:
release/release-units.toml - TypeScript release set:
release/typescript.mdand.github/workflows/release-typescript.yml - Frontend:
zenml-io/zenml-frontend-monorepo/.github/workflows/release-kitaru-ui.yml - Follow-up skills release: skills-release
Read AGENTS.md. Read plugins/AGENTS.md and plugins/DEVELOPMENT.md for plugin changes. Read FRONTEND-TESTING.md for core or UI work.
Do not create a tag, dispatch a publishing workflow, approve an environment, or publish an artifact without explicit user confirmation. A request to prepare a release authorizes a release PR only.
Select the release shape
Ask only for choices that cannot be derived from the repository and registries.
- Core: Release
kitaru, the selected UI, public images, the managed image, and Helm from one core tag. - One plugin: Release one selected Python plugin distribution. Do not release the UI or core.
- All plugins: Inspect and prepare every plugin release unit independently.
- Coordinated: Release core with its selected UI, then publish plugins that depend on that core version.
There is no separate bundle tag. The core tag publishes the Python package and deployables in one workflow.
Confirm the selected distributions, versions, frontend tag, publication order, and release commit before editing.
Discover release impact
Fetch current remote state and load the release inventory:
git fetch origin --prune --tags
uv run --no-project --with packaging==26.2 \
python scripts/release_units.py list --format json
For every selected unit, resolve its latest published tag. Compare that tag with origin/develop and inspect merged PRs in the range with git log, git diff, and gh pr view. Derive directly changed core and plugin units from impact-paths in release/release-units.toml. Read requires:* labels as release follow-up metadata, together with Release context, linked work, and existing changelog entries. A directly changed unit does not need a matching label when it will be published in the next applicable release. If its publication is intentionally deferred past that release, attach its exact release-label and record the intended timing in Release context.
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.
- today Changed · -14 lines 7dcfabb95e88
- 4d ago Changed · +8 lines a41f3aab01f2
- 5d ago Changed · +50 lines 5d683313d8de
- 9d ago First seen · 350 lines · 83 tokens per session scan A 89d91725aec9
kitaru-release is a skill published in the GitHub repository zenml-io/kitaru (282 stars, last pushed today), licensed Apache-2.0. It adds 83 tokens to every session and 5,867 once invoked, about $0.0004 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 skills, from other repositories
publish-site
Versioned site deploys to GitHub/Cloudflare/Netlify Pages.
github
GitHub via gh CLI: PRs, issues, reviews, repos, auth.
changelog
Turn a range of commits or merged PRs into a changelog entry grouped by change type. Use when the user asks for release notes, a changelog, or "what changed" between two points.
github-repo-management
Clone, create, fork, configure, and manage GitHub repositories. Manage remotes, secrets, releases, and workflows. Works with gh CLI or falls back to git + GitHub REST API via curl.
goal-issues-and-release
Clear the open issue backlog and then cut a release, in one autonomous run: use the batch-all-issues skill to resolve every open issue, then the goal-release skill to draft, merge, and see the release through publication. Never asks the user anything — every decision is made autonomously, and blockers are reported at…
goal-release
Cut a release end to end: use the draft-release skill to open the release PR and draft GitHub release, wait for CI to turn green, run the merge-pr skill to merge the release PR, then update the Homebrew formula from the published release assets. Use when the user wants to draft and merge a release in one go, or…