Borrowing it
Nothing to install: this file belongs to htlin222/hahow-mentor-agent. 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/htlin222/hahow-mentor-agent/main/.claude/skills/batch-draft-hahow/SKILL.mdgit clone --depth 1 https://github.com/htlin222/hahow-mentor-agentWrote 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/htlin222/hahow-mentor-agent/batch-draft-hahow)<a href="https://agentmods.dev/skills/htlin222/hahow-mentor-agent/batch-draft-hahow"><img src="https://agentmods.dev/badge/skills/htlin222/hahow-mentor-agent/batch-draft-hahow/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/htlin222/hahow-mentor-agent/batch-draft-hahow"><img src="https://agentmods.dev/badge/skills/htlin222/hahow-mentor-agent/batch-draft-hahow.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 | $0.00095 | $0.01168 |
| Opus 5 | $0.00048 | $0.00584 |
| Sonnet 5 | $0.00019 | $0.00234 |
| Haiku 4.5 | $0.00010 | $0.00117 |
Grade A, and why
batch-draft-hahow 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 10d 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 — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Batch-draft Hahow student questions
When this skill applies
User asks to triage / draft replies to multiple unanswered student questions
across the taught courses. For single-question replies, use the CLI's existing
hahow-mentor ask reply <id> directly instead.
Pre-flight checks
- Working directory is
hahow-mentor-agent(Makefile +src/hahow_mentor/). .envhasIDandPASSWORD.codexis on PATH (which codexreturns a path).~/.hahow-mentor/session.jsonexists, or runmake verifyto log in.
Workflow checklist
Create one TodoWrite entry per step so progress is visible to the user.
- Step 1 — refresh. Run
make refresh. This dumpsbuild/unread.jsonand downloads every attached image. Report the total count: "N unread+unresolved across M courses". - Step 2 — categorise. Print a numbered list grouped by kind: - Technical PS/InDesign — needs WebSearch + drafter - Course meta (作業需要 PS 嗎 / 講義在哪 / 英文版 / hahow logo) - Google+ — Google+ shut down 2019-04, drafter gets a stock note - Already resolved by user themselves — drafter gets a brief ack
- Step 3 — read images. For each entry where
q.image_urlsis non-empty, use the Read tool on~/.hahow-mentor/audits/discussion-<id>/images/image-00.png(and -01, -02, …) and write one Chinese sentence per id intobuild/image_notes.json. Cover: what is the screenshot showing, where the visible problem is. - Step 4 — WebSearch. For each technical question dispatch a
WebSearch query in batches of ≤5 per message (parallel). After every
batch summarise the result into
build/web_findings.json[id]— one or two short paragraphs. Skip WebSearch for non-technical buckets. - Step 5 — draft. Run
make draft. This skips ids that already have drafts in~/.hahow-mentor/drafts/. Usemake draft-forceonly if the user wants a re-roll. ~30 s per call × N questions; tell the user the expected wall time and run the command withrun_in_background=true. Do not poll the output file — wait for the notification. - Step 6 — status report. Run
make statusand paste the table. Stop. Wait for the user to pick which drafts to post.
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.
- 10d ago First seen · 93 lines · 95 tokens per session scan A 481d61e81082
batch-draft-hahow is a skill published in the GitHub repository htlin222/hahow-mentor-agent (1 stars, last pushed 3mo ago), licensed MIT. It adds 95 tokens to every session and 1,168 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 2026-08-31.
Other skills, from other repositories
kaggle-learner
This skill should be used when the user asks to "learn from Kaggle", "study Kaggle solutions", "analyze Kaggle competitions", or mentions Kaggle competition URLs. Provides access to extracted knowledge from winning Kaggle solutions across NLP, CV, time series, tabular, and multimodal domains.
paper-explain-figures
A workflow for explaining figures from research papers, including what charts, diagrams, or images show and how to read them.
accredible-certificates-automation
Automate Accredible Certificates tasks via Rube MCP (Composio). Always search tools first for current schemas.
blackboard-automation
Automate Blackboard tasks via Rube MCP (Composio). Always search tools first for current schemas.
cc-skill-continuous-learning
Development skill from everything-claude-code.
presentation-video
This skill should be used when the user asks to "make an animated presentation", "turn a pitch deck into a video", "convert slides/a deck to video", "make a presentation video", "build a deck video", "narrate a slide deck as a video", or "auto-advance slides synced to a voiceover". Covers rebuilding slides as motion…