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/issue-plannpx skills add guillermoscript/lms-front --skill issue-plangit 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 | $0.00090 | $0.01386 |
| Opus 5 | $0.00045 | $0.00693 |
| Sonnet 5 | $0.00018 | $0.00277 |
| Haiku 4.5 | $0.00009 | $0.00139 |
Grade A, and why
issue-plan 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.
How it starts
The opening of the file, as written. The whole thing — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Issue Plan — from issue URL to a posted plan of attack
The output of this skill is a plan someone else could execute: the issue comment is the public record of the approach, and it later seeds the PR body. Write it for the teammates who will read it on GitHub, not for the user in this chat. No code gets written or changed here — this skill is read-only on the codebase and write-only on the issue.
Repo facts (repo, gh user, board config) come from the gh-repo-config
skill; board moves go through gh-board. Neither being configured
blocks a plan — unconfigured pieces are skipped and noted.
1. Read the issue
Accept a full URL, #N, or a bare number. Gather everything in one pass:
gh issue view <N> --json number,title,body,labels,milestone,assignees,comments,url
Read the comments too — later comments often amend or overrule the original body. If the issue references other issues/PRs (an epic parent, a "relates to"), skim those for constraints. If the issue is genuinely ambiguous about what to build (not how — that's this skill's job), ask the user before going further.
If the issue is already assigned to someone else or already In Progress on the board, stop and ask the user before taking it over.
2. Survey the code
Before forming an opinion, survey the code the issue touches — read-only;
Explore subagents are good for this. Check the repo's CLAUDE.md/AGENTS.md
for documented gotchas (multi-tenancy, auth boundaries, basePath quirks,
dual databases, feature flags — whatever that repo calls out). The posture
is survey-first: the plan must be written well enough that someone with
zero session context could follow it.
3. Author the plan
A short plan, four parts:
- Root cause / current behavior — what the code does today and why that's the issue.
- Approach — what will change, in which files.
- Risks / blast radius — what else touches this code, weighing the gotchas found in the survey.
- Test plan — which checks will prove it works (commands + manual steps), using the repo's discovered build/lint/test commands.
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.
- 2d ago First seen · 118 lines · 90 tokens per session scan A da3bc66072e8
issue-plan is a skill published in the GitHub repository guillermoscript/lms-front (24 stars, last pushed 2d ago), licensed MIT. It adds 90 tokens to every session and 1,386 once invoked, about $0.0005 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。.