Borrowing it
Nothing to install: this file belongs to numikel/kprun. 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/numikel/kprun/main/.cursor/skills/prepare-release/SKILL.mdgit clone --depth 1 https://github.com/numikel/kprunWrote 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/numikel/kprun/prepare-release)<a href="https://agentmods.dev/skills/numikel/kprun/prepare-release"><img src="https://agentmods.dev/badge/skills/numikel/kprun/prepare-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/numikel/kprun/prepare-release"><img src="https://agentmods.dev/badge/skills/numikel/kprun/prepare-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 | $0.00041 | $0.01112 |
| Opus 5.5 | $0.00016 | $0.00445 |
| Sonnet 5.5 | $0.00008 | $0.00222 |
| Haiku 4.5 | $0.00004 | $0.00111 |
Grade A, and why
prepare-release scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Prepare release
Prepare a kprun release locally. No LLM calls in CI — all changelog writing happens here in the IDE.
Invocation
User runs /prepare-release X.Y.Z where X.Y.Z is semver without the v prefix (e.g. 0.2.0).
Mandatory checklist (follow in order)
1. Resolve commit range
git fetch --tags
PREV=$(git describe --tags --abbrev=0 2>/dev/null || echo "")
if [ -z "$PREV" ]; then
RANGE="first commit..HEAD"
else
RANGE="${PREV}..HEAD"
fi
git log $RANGE --oneline
git log $RANGE --format="%s"
If range is empty (no commits since last tag), stop and ask the user to confirm before writing an empty changelog.
2. Classify commits
Group git log subjects by Conventional Commits type:
| Type | Keep a Changelog section |
|---|---|
feat |
Added |
fix |
Fixed |
perf |
Changed |
refactor |
Changed |
docs |
Changed (or omit if internal-only) |
ci, build, chore |
omit unless user-facing |
feat!, fix!, footer BREAKING CHANGE: |
Changed + breaking note |
Write user-facing bullets in English. No raw SHAs in bullet text. Optional <details> footer with full commit list.
3. Write per-version file
Create docs/changelogs/vX.Y.Z.md:
- Format: Keep a Changelog 1.1.0
- Title/header includes version and date (UTC:
YYYY-MM-DDfromdate -u +%Y-%m-%d) - Sections (omit empty):
Added,Changed,Deprecated,Removed,Fixed,Security - Reference prior file
docs/changelogs/v0.1.0.mdfor tone and structure
4. Update root CHANGELOG.md
Prepend a new section at the top (after the intro paragraphs):
## [X.Y.Z] - YYYY-MM-DD
See [docs/changelogs/vX.Y.Z.md](docs/changelogs/vX.Y.Z.md) for details.
### Added
- (short summary bullets)
Keep root entries as summaries; full detail stays in per-version file.
5. Version bump
Update all three locations to X.Y.Z:
[workspace.package].versionin rootCargo.tomlcrates/kprun/Cargo.toml— usesversion.workspace = true(verify, do not duplicate)crates/kprun-core/Cargo.toml— usesversion.workspace = true(verify)
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.
- 2mo ago First seen · 125 lines · 41 tokens per session scan A 0f2bec9967a6
prepare-release is a skill published in the GitHub repository numikel/kprun (8 stars, last pushed 3d ago), licensed MIT. It adds 41 tokens to every session and 1,112 once invoked, about $0.0002 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 2026-08-31.
prepare-release compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| prepare-releasenumikel/kprun | Skill | 8 | 3d ago | MIT | A | 41 | Cursor |
| rea-changelog-updatemorluto/rea | Skill | 435k | today | MIT | A | 33 | Claude Code |
| codew-release-qa-sweepHmbown/CodeWhale | Skill | 41k | 5d ago | MIT | A | 31 | Claude Code, Codex |
| releaseHmbown/CodeWhale | Skill | 41k | 5d ago | MIT | A | 0 | Claude Code, Codex |
| skillshare-releaserunkids/skillshare | Skill | 2.9k | yesterday | MIT | A | 77 | Claude Code |
| skillshare-changelogrunkids/skillshare | Skill | 2.9k | yesterday | MIT | A | 134 | Claude Code |
| githubAtomicBot-ai/atomic-agent | Skill | 3.4k | 8d ago | MIT | A | 48 | Claude Code, Codex |