Borrowing it
Nothing to install: this file belongs to asta-nguyen/kamehadb. 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/asta-nguyen/kamehadb/main/.agents/skills/preparing-releases/SKILL.mdgit clone --depth 1 https://github.com/asta-nguyen/kamehadbWrote 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/asta-nguyen/kamehadb/preparing-releases)<a href="https://agentmods.dev/skills/asta-nguyen/kamehadb/preparing-releases"><img src="https://agentmods.dev/badge/skills/asta-nguyen/kamehadb/preparing-releases/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/asta-nguyen/kamehadb/preparing-releases"><img src="https://agentmods.dev/badge/skills/asta-nguyen/kamehadb/preparing-releases.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 | $0.00524 |
| Opus 5 | $0.00020 | $0.00262 |
| Sonnet 5 | $0.00008 | $0.00105 |
| Haiku 4.5 | $0.00004 | $0.00052 |
Grade A, and why
preparing-releases 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.
How it starts
The opening of the file, as written. The whole thing — 34 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Preparing Releases
Prepare a releasable commit first. Tag, push, and publish only with direct user instruction.
Release checklist
-
Inspect
git status --short, the intended diff, local/remotev*tags, and all six app-version files. If the worktree has unrelated changes or an existing tag conflicts with a manifest version, stop and ask for the intended release scope/version; never move or reuse an existing tag. -
Confirm the SemVer target with the user. Use
bump-versionto update exactlypackage.json, the desktop/sidecar/shared package files,tauri.conf.json, andCargo.toml. Never updatelanding/package.json. -
Turn
[Unreleased]intovX.Y.Zwith today’s date and add a fresh[Unreleased]. Keep entries concise and user-facing; remove empty, duplicate, dependency-only, and internal implementation notes. -
For new engines, major workflows, or product-description changes, update the five public surfaces in
AGENTS.md: landing hero, landing metadata, OG card, compare screenshots, andREADME.md. Regenerate visual assets only when their source changed. -
Verify release scope and quality:
pnpm typecheck pnpm --filter @kamehadb/desktop test pnpm build git diff --checkRun
cargo test --quietinapps/desktop/src-tauriafter Rust/native changes. Runnpm --prefix landing run buildafter landing or README changes. Confirm all six versions are identical and stage only intentional release files. -
Request explicit approval before committing, pushing, creating
vX.Y.Z, or triggering/publishing any release. After an explicitly authorized pushed tag, monitor.github/workflows/release.yml: it creates a draft release with macOS DMGs, Windows EXE/MSI, and Linux DEB/RPM. Do not expect an AppImage; publish the draft only with explicit final approval.
Guardrails
- A release tag is immutable: correct the next version instead of force-moving an existing tag.
- A dirty worktree is not a release candidate until its unrelated changes are separated or approved.
- Do not claim a release is ready without fresh command output from the checklist.
What ships with it
1 file 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 · 34 lines · 41 tokens per session scan A 039663e86e0f
preparing-releases is a skill published in the GitHub repository asta-nguyen/kamehadb (14 stars, last pushed 10d ago), licensed Apache-2.0. It adds 41 tokens to every session and 524 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
Cut a Memoria release. Version bump, CHANGELOG, CI workflows, Docker image. Use when publishing a new version.
product-multi-role-analysis
Analyze a product from documentation, websites, PDFs, articles, release notes, pricing pages, app listings, reviews, filings, or related links; save separate intermediate analyses from seven roles (user, investor, product manager, market operator, brand operator, competitor, partner), then synthesize a sourced…
dlt-connector
Connect SaaS data (HubSpot, Stripe, Salesforce, GitHub, Slack, etc.) to Wren Engine for SQL analysis. Guides the user through the full flow: install dlt, pick a SaaS source, set up credentials, run the data pipeline into DuckDB, then auto-generate a Wren semantic project from the loaded data. Use this skill whenever…
wren
Wren CLI for AI agents — a semantic SQL layer over 22+ databases (Postgres, MySQL, BigQuery, Snowflake, Spark, …). The actual workflow guides live inside the wren CLI itself; this is just a discovery stub. Use whenever the user asks a data question (how many, show me, top N, compare, trend, breakdown, metric, revenue…
git-expert
Expert-level Git version control with advanced workflows, branching strategies, and best practices for team collaboration. Use when the user mentions version control, collaboration, or workflow, or when the task involves Essential Git Commands, Advanced Git Techniques, Branching Strategies, or Conflict Resolution.
trellis-finish-work
Wrap up the current session: verify quality gate passed, remind user to commit, archive completed tasks, and record session progress to the developer journal. Use when done coding and ready to end the session.