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 TaewoooPark/MagLab --skill revision-lettergit clone --depth 1 https://github.com/TaewoooPark/MagLabWrote 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/taewooopark/maglab/revision-letter)<a href="https://agentmods.dev/skills/taewooopark/maglab/revision-letter"><img src="https://agentmods.dev/badge/skills/taewooopark/maglab/revision-letter/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/taewooopark/maglab/revision-letter"><img src="https://agentmods.dev/badge/skills/taewooopark/maglab/revision-letter.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 | $0.00068 | $0.00847 |
| Opus 5 | $0.00034 | $0.00424 |
| Sonnet 5 | $0.00014 | $0.00169 |
| Haiku 4.5 | $0.00007 | $0.00085 |
Grade A, and why
revision-letter 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 12d 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 — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
revision-letter — Point-by-point reviewer response letter skill
Overview
This skill drafts a structured revision response letter aligned with MagLab research integrity principles (§3.3) and the Appendix C bundle comms workflow.
Core principles:
- Every reviewer comment is quoted verbatim before the response.
- The AI does not invent new experimental data or results — only the author can supply those.
- All personalisation fields (editor name, page/line numbers, new data references) are
marked
[FILL]for the author to complete. - Output always begins with
HUMAN REVIEW REQUIRED. - The letter is never auto-sent — it is written to a file for human review.
Agent: maglab.authoring.comms.revision_letter.RevisionLetterAgent
CLI command: maglab comms revision
Inputs
| Key | Type | Required | Description |
|---|---|---|---|
review_decision |
str | Yes | Full journal decision letter containing reviewer comments |
comment_notes |
list[str] | No | Author notes per reviewer comment (leave empty to use [FILL]) |
tone |
str | No | formal (default) | respectful | assertive |
manuscript_orig |
str | No | Original manuscript excerpt (for context) |
manuscript_rev |
str | No | Revised manuscript excerpt (for context) |
Output
A CommsResult with:
text: Full revision letter starting withHUMAN REVIEW REQUIRED.fill_markers: List of[FILL]positions requiring author personalisation.word_count: Approximate word count.
Letter structure
HUMAN REVIEW REQUIRED
[FILL: Dear Dr. [FILL: editor name],]
We thank the reviewers for their careful reading of our manuscript.
Below we address each comment point by point.
---
Reviewer 1, Comment 1:
> [verbatim comment text]
Response:
[AI-drafted response based on author notes or [FILL]]
Change location: [FILL: page/line in revised manuscript]
---
[... additional comments ...]
Sincerely,
[FILL: Corresponding author name]
Workflow
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.
- 12d ago First seen · 102 lines · 68 tokens per session scan A 9a016986da01
revision-letter is a skill published in the GitHub repository TaewoooPark/MagLab (11 stars, last pushed 1mo ago), licensed MIT. It adds 68 tokens to every session and 847 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 2026-08-30.
Other skills, from other repositories
gwas-starter
Use this skill to run a deterministic local pass over GWAS summary statistics, flag common QC issues, and emit a compact interpretation plan for downstream clumping, heritability, and functional follow-up.
skimage-regionprops-feature-extraction
Use this skill to extract deterministic morphology and intensity features from a toy image with scikit-image regionpropstable.
protein-language-model-function-analysis-starter
Use this skill to validate protein FASTA inputs, extract deterministic smoke-safe embeddings, and run a reusable sequence-to-function triage flow that can later be swapped onto real ESM-2 or ProtT5 backends.
plantcv-plant-phenotyping-starter
Use this skill to generate a tiny synthetic plant image, segment it with PlantCV, and summarize simple morphology-style phenotyping measurements.
lifelines-kaplan-meier-starter
Use this skill to run a deterministic Kaplan-Meier survival analysis over a toy cohort and summarize per-group survival curves.
openmm-forcefield-assignment-starter
Use this skill to assign a simple water force field to a tiny PDB topology with OpenMM and summarize the resulting system.