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 yha9806/academic-writing-toolkit --skill readersgit clone --depth 1 https://github.com/yha9806/academic-writing-toolkitWrote 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/yha9806/academic-writing-toolkit/readers)<a href="https://agentmods.dev/skills/yha9806/academic-writing-toolkit/readers"><img src="https://agentmods.dev/badge/skills/yha9806/academic-writing-toolkit/readers/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/yha9806/academic-writing-toolkit/readers"><img src="https://agentmods.dev/badge/skills/yha9806/academic-writing-toolkit/readers.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 | $0.00049 | $0.02399 |
| Opus 5.5 | $0.00020 | $0.00960 |
| Sonnet 5.5 | $0.00010 | $0.00480 |
| Haiku 4.5 | $0.00005 | $0.00240 |
Grade A, and why
readers 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 6d 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 — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/readers — Reader Panel
What it answers, and what it does not
It answers what a first-time reader believes, remembers and could reuse after reading a part of the manuscript, set against the points the author wants carried (the intent card). It is how "does the contribution come across" becomes something counted rather than asserted.
It does not answer whether the paper is good, whether a sentence changed its meaning (the author judges that), or which single word is hard (word-level agreement with the author was too low to use). An eight-reader panel separates only large differences; do not report a one-round rise or fall as a result. The script prints these limits in every report.
Before running
- Intent card. The author's statement of who the reader is and the two to four points (M1, M2, ...) the reader
should carry away. The writing loop names it in
target.intent_card. If it lives outside the workspace'shuman/folder it is a draft, and the report says so. Do not write it for the author; draft it only when asked, and label it a draft. The template atexperimental/writing-loop/templates/intent-card.mdhas further sections (advantage sentence, narrative order, experiment roles, the scan and its acceptance checks); this skill reads only the reader and the points. - Directed questions (optional, recommended): one per suspected misreading or per point you need confirmed,
as
id<TAB>questionlines. Free-text summaries overstate misreadings; a directed question confirms one. Always consider one about reuse and one about which field the work belongs to. When the draft states few links between sentences, pass--ask-relations: it asks each reader for the two sentences between which they most had to guess how one follows from the other, quoted. Readers asked only what got in their way seldom name a missing link. The tally places each reader's two quotes at the turn between the sentences that hold them. Where more than half of the readers who named a place, and at least three, name the same turn, it says the order there may need changing: check that turn against the story page before adding a connector. A connector states the relation; it does not change which step comes first (one case, so a question, not a rule).
What ships with it
3 files 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.
- 6d ago Changed · +2 lines d574509e214f
- 8d ago Changed · +4 lines 6452c2682f15
- 17d ago Changed · +12 lines 536ea8bb97dd
- 18d ago Changed · +29 lines 6728041697b4
- 21d ago Changed · +2 lines e433f3b65d42
- 22d ago First seen · 86 lines · 49 tokens per session scan A ac7f247d4e48
readers is a skill published in the GitHub repository yha9806/academic-writing-toolkit (48 stars, last pushed yesterday), licensed MIT. It adds 49 tokens to every session and 2,399 once invoked, about $0.0002 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 2026-09-24.
Other skills, from other repositories
academic-cv
Write academic CVs, cover letters, research statements, teaching philosophies, diversity statements, and prepare for academic job applications. Use this skill whenever you need to create or improve an academic CV, write a research statement, develop a teaching philosophy, prepare application materials for faculty…
conference-presentation
Design and write conference posters, oral presentations, slide decks, and conference abstracts. Use this skill whenever you need to create a research poster, prepare slides for an academic talk, design a conference presentation, write a conference abstract, or prepare for Q&A. Trigger for: "design my conference…
latex-writer
Write, structure, and compile LaTeX documents for academic purposes. Use this skill whenever the user needs to write a LaTeX document, choose the right document class or packages, format equations, manage bibliographies, create figures and tables in LaTeX, troubleshoot errors, or prepare a journal-ready manuscript.…
preregistration-guide
Write and complete preregistrations for research studies before data collection or analysis. Use this skill when preregistering a study, writing a registered report, or understanding open science practices. Trigger for: "preregister my study," "how to write a preregistration," "OSF preregistration," "AsPredicted,"…
argumentation-engine
Build, analyse, strengthen, and evaluate academic arguments using formal argumentation frameworks. Use this skill whenever the user needs to construct a logical argument, write a critical analysis, respond to counterarguments, evaluate the strength of evidence, identify logical fallacies, or apply argumentation models…
figure-table-checker
Check, improve, and ensure compliance of figures and tables in academic papers. Use this skill whenever the user needs to verify figure or table formatting, choose error bar types, check colorblind accessibility, ensure APA or journal-specific compliance, create CONSORT or PRISMA flow diagrams, or fix common figure…