Borrowing it
Nothing to install: this file belongs to SzamosiMate/tapir-archicad-MCP. 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/SzamosiMate/tapir-archicad-MCP/master/.agents/skills/prepare-github-release/SKILL.mdgit clone --depth 1 https://github.com/SzamosiMate/tapir-archicad-MCPWrote 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/szamosimate/tapir-archicad-mcp/prepare-github-release)<a href="https://agentmods.dev/skills/szamosimate/tapir-archicad-mcp/prepare-github-release"><img src="https://agentmods.dev/badge/skills/szamosimate/tapir-archicad-mcp/prepare-github-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/szamosimate/tapir-archicad-mcp/prepare-github-release"><img src="https://agentmods.dev/badge/skills/szamosimate/tapir-archicad-mcp/prepare-github-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 | $0.00026 | $0.00450 |
| Opus 5.5 | $0.00010 | $0.00180 |
| Sonnet 5.5 | $0.00005 | $0.00090 |
| Haiku 4.5 | $0.00003 | $0.00045 |
Grade A, and why
prepare-github-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 18d 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
Prepare a GitHub release
Read the release procedure and
the release-note style. Run commands from the
repository root; scripts/release.py handles deterministic preparation.
- Determine the target version and previous release tag from the request or session. Ask when the target version is missing; do not choose one implicitly. Respect requests limited to notes or local review rather than creating a draft.
- Finish any requested generation and source reviews before release preparation, following the repository's existing workflows. Do not invoke an explicit-only generation skill unless it was requested.
- Run
python scripts/release.py bump VERSIONand inspect the version/lock diff. Include it in the reviewed source changes. Preserve unrelated work and follow the session's commit/push authorization. A draft requires committed, pushed HEAD. If a branch is needed, userelease/VERSION. - Inspect the actual previous-tag-to-release-commit diff, PRs and relevant reports; fetch origin's tags when needed. Write the descriptive notes to an OS temporary Markdown file. Omit attribution from this helper input: the helper appends GitHub's exact generated PR list, authors and contributor credits.
- Run
python scripts/release.py check, thenpython scripts/release.py draft --previous vPREVIOUS --notes-file TEMP_FILE. Revise an existing draft in its editor rather than automatically recreating it. Do not move a conflicting existing tag. - Return the draft link. The user edits, discards, or clicks Publish release; that click starts the publishing workflow. Do not publish the draft or upload to PyPI as part of preparing it.
- Report publishing failures against the same tag. Do not delete PyPI files or silently choose a different version.
Use the draft as the durable review surface. Do not create a release-state cache or extra per-step reports; retain existing generation reports when applicable.
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.
- 18d ago First seen · 38 lines · 26 tokens per session scan A 6a2c91ef0767
prepare-github-release is a skill published in the GitHub repository SzamosiMate/tapir-archicad-MCP (131 stars, last pushed 2d ago), licensed MIT. It adds 26 tokens to every session and 450 once invoked, about $0.0001 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 2026-10-20.
prepare-github-release compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| prepare-github-releaseSzamosiMate/tapir-archicad-MCP | Skill | 131 | 2d ago | MIT | A | 26 | Claude Code, Codex |
| release-announcementpaperclipai/paperclip | Skill | 111k | yesterday | MIT | A | 42 | Claude Code, Codex |
| releasethedotmack/claude-mem | Skill | 114k | yesterday | Apache-2.0 | A | 13 | Claude Code |
| release-notesphuryn/pm-skills | Skill | 28k | 8d ago | MIT | A | 57 | Claude Code |
| multi-agent-release-managerchromium/chromium | Skill | 25k | yesterday | BSD-3-Clause | A | 27 | Claude Code, Codex |
| pack-submitaeonfun/aeon | Skill | 788 | yesterday | MIT | A | 27 | Claude Code, Codex |
| updater_guidesiddsachar/row-bot | Skill | 1.7k | yesterday | Apache-2.0 | A | 22 | Claude Code, Codex |