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/rohitgehe05/mindpowers/draftingnpx skills add rohitgehe05/mindpowers --skill draftinggit clone --depth 1 https://github.com/rohitgehe05/mindpowersWhat 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 | $0.00061 | $0.02427 |
| Opus 5 | $0.00030 | $0.01213 |
| Sonnet 5 | $0.00012 | $0.00485 |
| Haiku 4.5 | $0.00006 | $0.00243 |
Grade A, and why
drafting 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 — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Drafting
Overview
The second step in the mindpowers loop: shape (mindstorming) -> draft (drafting) -> review (reviewing-docs) -> remember (calibrating). Mindstorming turns a rough idea into a locked spec. Drafting turns that locked spec into the finished document, holding it to the standards baked into the matched template.
Drafting does not re-litigate the spec. The thinking already happened. This skill's job is faithful, high-quality execution: realize every section, honor every exclusion, apply the template's hard requirements, and flag any deviation instead of silently making one.
User-Facing Language
Think precisely; respond plainly. Use common words and short sentences. Explain an unavoidable technical term the first time it appears, and give one short example when a rule could be misunderstood. For a material conclusion about the draft, a blocker, or a deviation, give a compact explanation: the recommendation or conclusion, what you checked, the main reasons, uncertainty, and the next step. Do not dump internal machinery. If the user says the explanation is unclear, explain it again from scratch.
Input Contract
This skill needs a spec with status: locked from docs/mindpowers/specs/.
- Find the spec. Use the one the user names, or the most recent spec in
docs/mindpowers/specs/if the request is ambiguous (e.g. "draft it" right after a mindstorming session). Also check legacydocs/brainstorm/if it exists and nothing newer is indocs/mindpowers/specs/. - Status is
draft. Do not draft from it. Tell the user the spec isn't locked yet, and ask whether to lock it now or go back to mindstorming to finish shaping it. - Status is
superseded. Warn the user this spec was superseded (and by what, if the frontmatter or a newer spec says so). Confirm they still want to draft from it before proceeding. - No spec exists for the ask. Do not draft cold. Give one short pitch for shaping the audience, goal, and constraints first, something like "I don't see a spec for this. Want to shape the audience, goal, and constraints first so the draft has something clear to follow?" If the user confirms, switch to
mindstorming; do not switch before confirmation. Respect whatever the user decides. If they insist on skipping it, draft anyway, but say plainly that the quality bars (audience fit, standards, anti-pattern checks) will be weaker without a spec to hold the draft to.
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 · 106 lines · 61 tokens per session scan A 9f702d36f4d8
drafting is a skill published in the GitHub repository rohitgehe05/mindpowers (5 stars, last pushed 25d ago), licensed MIT. It adds 61 tokens to every session and 2,427 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
finishing-a-development-branch
Use when implementation is complete, all tests pass, and you need to decide how to integrate the work.
story-deslop
网文去AI味。检测并清除文本中的AI写作痕迹，让文字回归自然、非模板化。触发方式：/story-deslop、/去AI味、「去AI味」「这篇太AI了」「网文去AI味」。.
story
网络小说工具箱主入口。根据用户需求自动路由到对应 skill，并可管理作者习惯、启动本地 Dashboard。触发方式：/story、$story、/story dashboard、/网文、「我想写小说」「记住我的写作习惯」「打开工作台」「检查更新」。.
brainstorming-research-ideas
Guides researchers through structured ideation frameworks to discover high-impact research directions. Use when exploring new problem spaces, pivoting between projects, or seeking novel angles on existing work.
aws-wechat-article-topics
公众号选题｜爆款标题｜热点追踪｜系列策划 — 公众号 AI 选题与标题生成，覆盖热点调研、选题策划、起标题、写摘要、系列排期。面向自媒体编辑、内容运营。触发词（单独触发仅限对已有标题/摘要的修改）：「改标题」「换个标题」「重起标题」「优化标题」「标题再想想」「换个标题试试」「改摘要」「重写摘要」「优化摘要」「摘要再优化下」。新做选题、起新标题、策划系列/内容日历、追热点都请走 aws-wechat-article-main；需要多环节串联（写+审+排+配图+发）也走 main。.
higgsfield
Use this skill whenever the user asks anything about Higgsfield AI — writing or refining video/image prompts, choosing a model (Kling, Sora 2, Veo, Wan, Seedance, Minimax Hailuo, DoP, Soul, Nano Banana, Seedream, Flux, GPT Image, etc.), camera controls, named motion presets, Soul ID character consistency, Cinema…