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/guillermoscript/lms-front/ship-prnpx skills add guillermoscript/lms-front --skill ship-prgit clone --depth 1 https://github.com/guillermoscript/lms-frontWhat 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 | $0.00144 | $0.02477 |
| Opus 5 | $0.00072 | $0.01239 |
| Sonnet 5 | $0.00029 | $0.00495 |
| Haiku 4.5 | $0.00014 | $0.00248 |
Grade A, and why
ship-pr 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 3d 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 — 197 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ship PR — from pushed branch to announced, reviewable PR
The PR body is the QA script and the announcement is what actually gets the work reviewed — write both for the teammates who consume them, not for the user in this chat. Everything GitHub or Slack sees is a permanent record: normal, professional, full-sentence English.
Config (PR template path, Slack channel, default reviewer) comes from
.claude/gh-workflow.config.json — resolve missing pieces via the
gh-repo-config skill. Board operations go through the gh-board
skill. Neither being configured blocks a PR; unconfigured features are
skipped and noted.
Division of labor
The main agent does exactly two kinds of work here: author content (the PR title + body, the Slack message — these need session context and judgment) and decide metadata (labels, milestone, size — deciding takes judgment, applying doesn't). Every mechanical action — creating the PR, applying labels/milestone/assignee, board moves, the Slack post — goes to a subagent that receives the authored content plus exact commands and returns only what's needed next (PR URL, board item id).
Two rules keep that delegation honest — a subagent that can't find an authored file will fabricate a fluent replacement, and every signal except the content itself will report success:
- Mark every noun in the prompt. Each file or text is given or
to-produce. For every given file: "This file already exists and is
final — do NOT create, edit, or overwrite it; only pass its path to the
command." Authored text travels with "post this EXACTLY, verbatim". Name
authored files uniquely (
pr-<N>-body.md, notbody.md) so a stray write is detectable. - Verify content, not exit codes. After the subagent runs, fetch what
was actually published (
gh pr view <PR> --json title,body, the posted comment viagh api .../comments/<id> -q .body, the Slack message) and compare it to what you authored. If it drifted, edit in place —gh pr edit/gh api -X PATCHkeeps thread position, unlike delete-and-repost — using corrected content written to a fresh, uniquely-named file, not the possibly-clobbered original.
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.
- 3d ago First seen · 197 lines · 144 tokens per session scan A a05df1201be6
ship-pr is a skill published in the GitHub repository guillermoscript/lms-front (24 stars, last pushed 3d ago), licensed MIT. It adds 144 tokens to every session and 2,477 once invoked, about $0.0007 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
api-development
FastGPT API 开发规范。重点强调使用 zod schema 定义入参和出参,在 API 文档中声明路由信息,编写对应的 OpenAPI 文档,以及在 API 路由中使用 schema.parse 进行验证。.
ci-workflow-sync
FastGPT CI workflow 双轨同步。当用户修改或新增 .github/workflows/ 下的 GitHub Actions workflow 时必须触发：同步更新 .forgejo/workflows/ 对应文件保持功能一致，或判断是否需要新建 Forgejo 版本。涉及 CI、GitHub Actions、Forgejo Actions、镜像构建、container registry、artifact、workflow yaml 改动、build- workflow、test- workflow 时也使用此技能。即使用户只提到"改一下 CI"或"加个 workflow"也应触发。.
prompt-optimize
Expert prompt engineering skill that transforms Claude into "Alpha-Prompt" - a master prompt engineer who collaboratively crafts high-quality prompts through flexible dialogue. Activates when user asks to "optimize prompt", "improve system instruction", "enhance AI instruction", or mentions prompt engineering tasks.
deprecate-workflow-node
当用户需要弃用一个工作流节点（保留向后兼容、隐藏出模板面板）时触发该 skill。FastGPT 工作流节点的弃用流程标准化封装，覆盖模板、Dispatcher、UI 引用等所有需要改动的位置。.
doc-i18n
将 FastGPT 文档从中文翻译为面向北美用户的英文。当用户提到翻译文档、i18n、国际化、translate docs、新增/修改了中文文档需要同步英文版时，使用此 skill。也适用于用户要求检查文档翻译缺失、批量翻译、或对比中英文文档差异的场景。.
pr-change-analysis
手动触发的 FastGPT PR 或本地分支变更梳理技能。仅当用户显式调用 $pr-change-analysis 时使用；用于 reviewer 分析一个 GitHub PR 或当前本地分支相对 upstream/main 的需求变更、影响范围、代码质量与代码风格，不用于自动审查触发。.