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 ShaishavMaisuria/research-paper-lifecycle-skills --skill work-with-overleafgit clone --depth 1 https://github.com/ShaishavMaisuria/research-paper-lifecycle-skillsWrote 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/shaishavmaisuria/research-paper-lifecycle-skills/work-with-overleaf)<a href="https://agentmods.dev/skills/shaishavmaisuria/research-paper-lifecycle-skills/work-with-overleaf"><img src="https://agentmods.dev/badge/skills/shaishavmaisuria/research-paper-lifecycle-skills/work-with-overleaf/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/shaishavmaisuria/research-paper-lifecycle-skills/work-with-overleaf"><img src="https://agentmods.dev/badge/skills/shaishavmaisuria/research-paper-lifecycle-skills/work-with-overleaf.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 | $0.00211 | $0.01141 |
| Opus 5 | $0.00105 | $0.00571 |
| Sonnet 5 | $0.00042 | $0.00228 |
| Haiku 4.5 | $0.00021 | $0.00114 |
Grade A, and why
work-with-overleaf 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 11d 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 — 44 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Work With Overleaf
Most academics keep their .tex in Overleaf, not on disk — so this skill gets an Overleaf project into a local working copy the rest of the toolkit can act on (preflight-check, polish-prose, verify-citations, match-style, …), then helps sync the changes back. It's the on-ramp; the other skills do the work.
Pick the path that matches the account
Overleaf exposes three ways to move a project in and out. Re-verify the current method and whether it's premium before relying on it against Overleaf's live documentation, because account features and menu names can change. As of the last check:
| Path | Who | How |
|---|---|---|
| Git integration (recommended) | Premium / Server Pro 4.0+ | Project → Menu → Git; copy the git clone https://git.overleaf.com/<id> command. Authenticate with an Overleaf token (token-based auth). Work locally, then git pull / git push. Branch is main (older clones may be master). |
| GitHub synchronization | Premium | Link the project to a GitHub repo (Menu → GitHub); sync both ways. Run the skills on the GitHub clone you already have locally. |
| Download ZIP | Free (everyone) | Menu → Download → Source. Work locally; there is no auto-merge — re-upload changed files in the Overleaf editor, or paste edits back. Best for a one-shot check. |
If the user isn't sure which they have, ask; don't assume premium.
Process
- Establish the local copy. Determine the path above and get the project local (clone, use the existing GitHub clone, or unzip the download). Confirm the main
.texand.bibare present. - Run the requested skills on the local files exactly as normal —
preflight-checkfor desk-reject risk,polish-prose/match-stylefor the writing,verify-citationsfor the.bib,assess-paperfor the full read. Write outputs topaper-workspace/. - Review changes before syncing. Show the author a diff of what changed. Never push automatically — academic drafts are shared/co-authored and an unreviewed push can clobber a collaborator's edits.
- Sync back by the same path:
git push(Git integration), commit+push to the linked GitHub repo (sync), or tell the author exactly which files to re-upload (ZIP). For Git/GitHub, confirm first and surface any merge conflicts rather than forcing. - Compile sanity. Note that Overleaf compiles server-side; if the local edits use a package/option Overleaf's TeX Live version may differ on, flag it so the author recompiles on Overleaf before relying on the PDF.
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.
- 11d ago First seen · 44 lines · 211 tokens per session scan A 9953021b9867
work-with-overleaf is a skill published in the GitHub repository ShaishavMaisuria/research-paper-lifecycle-skills (42 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 211 tokens to every session and 1,141 once invoked, about $0.0011 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
aaai-reproducibility
Use when strengthening an AAAI paper's reproducibility checklist (placed after references), experimental traceability, seed and hyperparameter reporting, compute and cost disclosure, dataset access and licensing, code/data ZIP readiness, and the claim-to-evidence map that Phase-1 reviewers use to judge rigor across…
aaai-submission
Use when auditing an AAAI main technical track submission for OpenReview readiness, double-blind anonymity, page limits, reproducibility checklist, supplementary material, author limits, multiple-submission policy, and AAAI AI-use policy compliance.
acl-author-response
Use when drafting an ACL author response inside an ACL Rolling Review cycle on OpenReview, covering the response window before meta-review, reviewer discussion dynamics, score-change strategy, flagging review issues to the area chair, anonymity rules, and deciding between responding now versus revising for a later ARR…
acl-camera-ready
Use when preparing an accepted ACL main-conference or Findings paper for camera-ready, covering the extra content page, de-anonymization and acknowledgements, AI-assistance disclosure, keeping the Limitations section, ACL Anthology metadata and CC BY 4.0 publication, meta-review-driven edits, and presentation-mode…
acl-related-work
Use when positioning an ACL submission against the NLP literature, covering ACL Anthology citation practice, arXiv-versus-published version citation, concurrent LLM-era preprints, prior-cycle ARR resubmission overlap, anonymity-preserving self-citation, and the fast-moving baseline problem in computational linguistics.
acl-reproducibility
Use when strengthening reproducibility evidence for an ACL paper reviewed through ACL Rolling Review, covering the Responsible NLP checklist end to end, hyperparameter and compute reporting, prompt and decoding disclosure for LLM experiments, data contamination auditing, variance across runs, and checklist-to-paper…