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 castorini/castorini-skills --skill castorini-releasegit clone --depth 1 https://github.com/castorini/castorini-skillsWrote 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/castorini/castorini-skills/castorini-release)<a href="https://agentmods.dev/skills/castorini/castorini-skills/castorini-release"><img src="https://agentmods.dev/badge/skills/castorini/castorini-skills/castorini-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/castorini/castorini-skills/castorini-release"><img src="https://agentmods.dev/badge/skills/castorini/castorini-skills/castorini-release.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00058 | $0.00372 |
| Opus 5 | $0.00029 | $0.00186 |
| Sonnet 5 | $0.00012 | $0.00074 |
| Haiku 4.5 | $0.00006 | $0.00037 |
Grade A, and why
castorini-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 12d 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
Castorini Release
PyPI/TestPyPI publish workflow for nuggetizer, ragnarok, rank_llm, and umbrela.
Start with the reference checklist and use the bundled preflight script before uploading anything.
Reference Files
references/pypi-checklist.md— Step-by-step checklist with commandsreferences/release-sequence.md— Supported repos and the high-level release sequence
Preflight Script
Run the preflight checks before publishing:
bash skills/castorini-release/scripts/preflight.sh <repo-path>
This verifies:
- Package builds successfully
- twine check passes (metadata, description rendering)
- No uncommitted changes
- Version is bumped from the last release
Gotchas
- All four repos use
bumpver; confirm the version change landed in the tracked files before you build. uv buildshould be run from the package root, not from the monorepo root or a skill directory.- A TestPyPI upload only proves packaging and upload credentials; it does not guarantee PyPI will accept the same distribution later.
- TestPyPI installs often need
--extra-index-url https://pypi.org/simple/because transitive dependencies may not exist on TestPyPI. - Tagging rules and release-note locations are not fully standardized across the repos, so verify the target repo before creating the final tag.
What ships with it
3 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.
- 12d ago First seen · 41 lines · 58 tokens per session scan A 09d37df9db35
castorini-release is a skill published in the GitHub repository castorini/castorini-skills (2 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 58 tokens to every session and 372 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
python-packaging
Create distributable Python packages with proper project structure, setup.py/pyproject.toml, and publishing to PyPI. Use when packaging Python libraries, creating CLI tools, or distributing Python code.
pypi-release
This skill should be used when releasing tunacode-cli to PyPI. It keeps the existing local release checks, then hands the actual PyPI upload to a GitHub Actions workflow that uses the repository's PYPIAPITOKEN secret.
changelog-python-cliff-skill
Generate automated changelogs for Python projects using git-cliff with PEP 440 versioning support.
plainx-release
Releases plainx packages with version suggestions, changelog generation, and git tagging. Use when releasing a package to PyPI.
python-release
Release engineering for Python projects on uv — static versioning in pyproject.toml exposed via importlib.metadata, building the sdist and wheel with uv build, publishing to PyPI with uv publish via Trusted Publishing (OIDC, no token), tag-triggered GitHub Actions releases, CI running ruff/ty (or pyright)/pytest with…
release
Prepare and execute a Python package release with verification steps. Use for releasing Python packages with uv and ruff.