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 glebis/claude-skills --skill cull-releasegit clone --depth 1 https://github.com/glebis/claude-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/glebis/claude-skills/cull-release)<a href="https://agentmods.dev/skills/glebis/claude-skills/cull-release"><img src="https://agentmods.dev/badge/skills/glebis/claude-skills/cull-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/glebis/claude-skills/cull-release"><img src="https://agentmods.dev/badge/skills/glebis/claude-skills/cull-release.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00045 | $0.00404 |
| Opus 5 | $0.00023 | $0.00202 |
| Sonnet 5 | $0.00009 | $0.00081 |
| Haiku 4.5 | $0.00005 | $0.00040 |
Grade A, and why
cull-release scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Cull Release
Principle
Orchestrate Cull's repository-enforced phases; never recreate release logic in
the skill. Read references/phase-contracts.md before acting.
Start or resume
- Resolve Cull from a matching current origin, absolute
CULL_REPO, or$HOME/ai_projects/cull. - For a new release, require explicit
patch|minor|major; never infer it. - Use cull-release-check. Stop on every blocker.
- Use cull-release-prepare in its isolated worktree.
- Use cull-release-publish after preparation. An explicit complete-release request already authorizes publication: Do not ask for a second publication confirmation.
- Use cull-release-verify after GitHub publication and Homebrew promotion.
- On interruption, derive the last verified state from commit, tag, workflow, artifacts, release, and tap evidence. Resume the first incomplete phase; do not repeat completed work.
- Route every mismatch or failed phase through cull-release-recover.
Before the first tag of a cycle, read
references/release-lessons-2026-09.md — it documents the failure modes that
cost four burned attempts in the v0.6.x cycle (record-anchor vs workflow-gate
mismatch, dependabot staleness races, closed-bead bd filter, provenance type
drift) and the exact tag-time sequence that avoids them.
Completion report
Report version, release commit, annotated tag object, workflow run, artifact
hashes, release URL, Homebrew tap commit, and final
post-publish-verified state. Do not print secret values.
What ships with it
5 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.
- 6d ago Changed · +6 lines 6e7a9383517c
- 10d ago First seen · 33 lines · 45 tokens per session scan A 58d9a45759da
cull-release is a skill published in the GitHub repository glebis/claude-skills (374 stars, last pushed 7d ago), licensed MIT. It adds 45 tokens to every session and 404 once invoked, about $0.0002 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
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.
multi-agent-release-manager
Cleans up the workspace, formats code, runs presubmit checks, and uploads CLs to Gerrit.
release-notes
Generate user-facing release notes from tickets, PRDs, or changelogs. Creates clear, engaging summaries organized by category (new features, improvements, fixes). Use when writing release notes, creating changelogs, announcing product updates, or summarizing what shipped.
pack-submit
Package one of this agent's own skills as a standalone community pack and submit it to the aeon registry as a PR.
updater_guide
Guidance for checking for and installing Row-Bot updates.
nvca-chart-release
Release NVCA Operator chart changes from the native monorepo source to the vendored Helm chart. Use when updating the vendored NVCA Operator chart, changing NVCA image refs, publishing helm-nvca-operator, or validating the chart against a self-managed control plane.