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 agentmods add skills/frostney/gocciascript/create-releasenpx skills add frostney/GocciaScript --skill create-releasegit clone --depth 1 https://github.com/frostney/GocciaScriptWhat 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 | $0.00054 | $0.00821 |
| Opus 5 | $0.00027 | $0.00411 |
| Sonnet 5 | $0.00011 | $0.00164 |
| Haiku 4.5 | $0.00005 | $0.00082 |
Grade A, and why
create-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 2d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- create-release — 88% identical, 14 lines differ
How it starts
The opening of the file, as written. The whole thing — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create release
Prepare a release whose tag contains its changelog, then publish through exactly one evidence-backed path when publication is authorized.
Authorization
- Prepare: determine the version, update changelog/version declarations, validate, and open the release PR. Requests to prepare, bump, or generate notes authorize only this stage.
- Publish: after the PR merges, create or trigger the tag/release through the
repository's established publisher. Requests to cut, tag, publish, or run
/create-releaseauthorize this stage too. - When ambiguous, perform Prepare only.
Invariants
- The changelog and version bump land before the tag, through a squash-merged PR.
- Use the repository's configured tools and current documentation. Regenerate generated changelogs rather than hand-editing them.
- Use an explicit version or recommend one from unreleased conventional commits and wait for the user's decision.
- Run the declared release-relevant gate and report only observed results.
- Never amend, force-push, force-update a tag, skip hooks, or publish through more than one path.
Prepare
- Resolve the authorization stage, remote default branch, clean working tree, changelog/version tooling, last release, remote tags, workflows, and release documentation.
- Stop if there are no releasable commits.
- Validate a supplied version, or recommend and confirm the next version from unreleased commits.
- Create a release branch from the fresh remote base.
- Generate the changelog section and update every authoritative version declaration using project tooling. Do not invent a manifest bump when the project derives its version from tags.
- Run the release-relevant project gate, commit
chore(release): <version>, and open a draft release PR through/create-pr. Include the changelog section and observed validation. Stop here for Prepare-only requests.
Publish
- Use
delivery-waitto await and verify the squash merge for the exact PR head; never tag the open PR branch. - Refresh the merged base, then re-read the actual workflow YAML and release documentation. Identify separate owners for tag creation, GitHub release creation, artifact signing, and registry publishing.
- Select exactly one route:
- workflow owns tag and release: trigger or monitor it only;
- agent owns tag, workflow owns release: push the verified tag once, then monitor;
- workflow owns tag, agent owns release: verify its tag, then create one GitHub release;
- agent owns both: only when no workflow owns either action, push the verified tag once and create one release.
- Stop when ownership is ambiguous or documentation and workflow disagree.
- Execute only the selected route and verify the final tag target, release,
workflow result, artifacts, and registry state that the route owns. Use the
helper's
wait workflow-terminal,wait tag-target, andwait release-assetsoperations for those GitHub transitions; do not monitor unchanged state through model turns.
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.
- 2d ago First seen · 81 lines · 54 tokens per session scan A 273c29240f92
create-release is a skill published in the GitHub repository frostney/GocciaScript (20 stars, last pushed 6d ago), licensed MIT. It adds 54 tokens to every session and 821 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 2026-08-30.
Other skills, from other repositories
qcad
Use when editing DXF files with a professional open-source 2D CAD application — CAM output, part libraries, isometric projection. QCAD: open-source 2D CAD with DXF as native format, scriptable via ECMAScript.
oxc-docs
Comprehensive reference for the JavaScript Oxidation Compiler (Oxc) — a collection of high-performance JavaScript tools written in Rust. Covers parser design (lexer, AST, parser, errors, semantic analysis), architecture (parser, linter, test infrastructure, AST tools), ECMAScript specification and grammar, performance…
git-step-commit
Analyze Git changes, split them into coherent commits, infer message language and format, optionally close supplied GitHub issues, and execute safely. Manage persistent global or repository preferences for review versus direct submission and automatic or specified commit-message language through native Git config.…
manage-prd-docs
Automatically manage product requirements across current decisions in docs/PRD.md and docs/prd/, mature future plans under docs/plans/, and active implementation under docs/work/. Use whenever the conversation discusses, clarifies, versions, plans, implements, completes, splits, or migrates a product requirement or…
modernize-ecmascript
当 Agent 编写或修改 JavaScript、TypeScript,用户要求按指定环境、输出版本、ES20xx 或具体语法编写代码,询问某项 ECMAScript 语法、标准内置 API 或提案能否采用,或者要求审查仓库中可简化、可现代化的写法时,应使用本 Skill。围绕目标文件真实经过的解析器、转换器和输出目标判断新语法能否安全采用,并按需读取 TC39 Atlas 的提案阶段、官方仓库、polyfill 与实现线索。.
codebase-audit
Audits the current repository for systemic correctness, architecture, churn, simplification, clarity, test value, and operational risks using current source and reproducible probes. It can delegate evidence gathering across bounded capability and perspective lanes. Use when the user runs /codebase-audit or asks for an…