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 skills add WALKERKILLER/Look-Tongji-Notes --skill notegit clone --depth 1 https://github.com/WALKERKILLER/Look-Tongji-NotesWrote 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/walkerkiller/look-tongji-notes/note)<a href="https://agentmods.dev/skills/walkerkiller/look-tongji-notes/note"><img src="https://agentmods.dev/badge/skills/walkerkiller/look-tongji-notes/note/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/walkerkiller/look-tongji-notes/note"><img src="https://agentmods.dev/badge/skills/walkerkiller/look-tongji-notes/note.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 | $0.00029 | $0.01713 |
| Opus 5.5 | $0.00012 | $0.00685 |
| Sonnet 5.5 | $0.00006 | $0.00343 |
| Haiku 4.5 | $0.00003 | $0.00171 |
Grade A, and why
note 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 1mo 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 — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Note
Generate detailed study notes from lecture transcript and slides.
When to Use
- User says
/noteor "write notes for this lecture". - After transcribing a lecture, the user wants a structured Markdown study note.
Workflow
- Default combined command:
python "<SKILL_DIR>/../../scripts/look_tongji.py" note --course-id "<ID>" --sub-id "<ID>"
- With supplementary materials:
python "<SKILL_DIR>/../../scripts/look_tongji.py" note \
--course-id "<ID>" --sub-id "<ID>" \
--material "slides-from-teacher=/path/to/file.pdf"
- The CLI runs transcript + slide in parallel, then the agent writes notes.
Important: note Re-Runs Transcription
note always re-downloads the video and re-runs ASR, even if the lecture was already transcribed. This is by design — note = transcribe + slide + note in one combined operation.
If you already ran transcribe separately, do NOT run note. Instead:
- Run
slideto download slides (if not already done) - Write the note manually using the existing SRT/TXT + slides
This saves ~4 minutes of re-downloading and re-transcribing per lecture.
Non-Interactive / Batch Flags
When scripting or working non-interactively:
| Flag | Description |
|---|---|
--no-slide |
Skip slide download (transcript only) |
--no-material-prompt |
Skip "any supplementary materials?" prompt |
For --no-material-prompt, use with --material to supply materials non-interactively:
python "<SKILL_DIR>/../../scripts/look_tongji.py" note \
--course-id "<ID>" --sub-id "<ID>" \
--no-material-prompt \
--material "slides=/path/to/file.pdf"
Agent Responsibilities
After the CLI finishes, the agent must:
A. Generate Timeline Outline
- Use SRT subtitles to produce a concise timeline in Simplified Chinese.
- Format:
MM:SS-MM:SS：课程阶段内容 - 10-20 segments for a typical 60-120 min lecture.
- Validate with:
python "<SKILL_DIR>/../../scripts/timeline_tools.py" timeline-normalize
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.
- 1mo ago First seen · 161 lines · 29 tokens per session scan A 8fa3709de4bf
note is a skill published in the GitHub repository WALKERKILLER/Look-Tongji-Notes (51 stars, last pushed today), licensed MIT. It adds 29 tokens to every session and 1,713 once invoked, about $0.0001 per session on Opus 5.5. 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
agent-challenges
Agent skill for challenges - invoke with $agent-challenges.
moai-workflow-jit-docs
Enhanced Just-In-Time document loading system that discovers, loads, and caches relevant documentation based on user intent and project context. Use when users need specific documentation on demand.
continuous-learning
Pattern extraction, confidence-scored evaluation, skill creation, organization, versioning, and cross-project export pipeline.
goga-discover
Interview the user relentlessly about a decision until every branch of the design tree is resolved, then record the result as a short ADR.
land
Build a stepped deck an audience works through until one thing of it stays with them. Use when the user needs an audience to come away holding one thing.
toy
Build a world the human drives until how a thing behaves is intuitive. Use when the user needs to hold how something behaves and reading has not made it intuitive.