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 Mexregkan/claude-for-researchers --skill overleaf-syncgit clone --depth 1 https://github.com/Mexregkan/claude-for-researchersWrote 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/mexregkan/claude-for-researchers/overleaf-sync)<a href="https://agentmods.dev/skills/mexregkan/claude-for-researchers/overleaf-sync"><img src="https://agentmods.dev/badge/skills/mexregkan/claude-for-researchers/overleaf-sync/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/mexregkan/claude-for-researchers/overleaf-sync"><img src="https://agentmods.dev/badge/skills/mexregkan/claude-for-researchers/overleaf-sync.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Tool Misuse · line 98 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- high Privilege Escalation · line 110 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
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 | $0.00000 | $0.01745 |
| Opus 5 | $0.00000 | $0.00873 |
| Sonnet 5 | $0.00000 | $0.00349 |
| Haiku 4.5 | $0.00000 | $0.00175 |
Grade A, and why
overleaf-sync 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 — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.
overleaf-sync
Sync a local git clone of a shared Overleaf project: pull collaborators' latest, check whether Overleaf has moved ahead, or (only on explicit request) publish your local edits back — without ever erasing collaborators' work.
Background: the setup this skill assumes
Overleaf exposes each project as a git remote (Overleaf menu → Sync → Git; paid
feature). The shared project is cloned into a subfolder of your repo — Overleaf/
by convention — which is its OWN git repo, separate from your project's repo.
- Remote
origin=https://git.overleaf.com/<project-id>. - Auth is an Overleaf git token (
olp_…), stored in the OS keychain viagit credentialso pulls are non-interactive (usernamegit, not your email). - Branch layout inside
Overleaf/:master— pristine mirror of Overleaf. Only ever updated bygit pull. NEVER edit here.local-edits— where you edit offline.
- Push is physically disabled as a safety net:
remote.origin.pushurlis set tono_push, sogit pushfails until deliberately re-enabled. Clone,fetch, andpullonly READ from Overleaf and cannot change the shared project; onlypushwrites. Overleaf/should be in your project's top-level.gitignoreso the shared paper is never pushed to your personal repo. (See the one-time setup note at the end.)
When to invoke
/overleaf-sync [status|pull|diff|publish] — default action is status.
Use status/pull/diff freely (read-only w.r.t. Overleaf). Use publish ONLY when
the user explicitly says to publish/push, and treat it as the one dangerous operation.
Preconditions (check first, every time)
Overleaf/exists and is a git repo:git -C Overleaf rev-parse --git-dir. If not, stop and point the user to the one-time setup at the end of this file; do not improvise.- Run all git commands with
-C Overleaf. If the project root path has spaces, quote it; theOverleafclone dir itself should have no spaces.
Actions
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 · 125 lines · 0 tokens per session scan A b2893c965994
overleaf-sync is a skill published in the GitHub repository Mexregkan/claude-for-researchers (52 stars, last pushed 7d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,745 tokens. 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
pre-commit-audit
Deliver a fast pre-commit safety scan: file size, anonymity (author / affiliation strings in tex/bib), hardcoded secrets, and invisible-Unicode carriers. Use when the user requests a fast pre-commit safety scan: file size, anonymity (author / affiliation strings in tex/bib), hardcoded secrets, and invisible-Unicode…
review-response
Systematic reviewer response workflow: parse comments, classify by severity, develop response strategy, write structured rebuttal. Use when asked to 'write rebuttal', 'respond to reviewers', 'draft review response', or 'handle R&R'.
latex-diff
Compare two LaTeX files, project directories, or Git revisions and produce human-readable plus machine-readable severity-graded semantic changes. Use when determining what changed between manuscript versions or preparing a revision audit bundle. Not for proofreading one version; use $proofread.
worktree-execution
Creates, pins, and cleans isolated Git worktree pairs for comparison trials. Use only when a Rashomon prompt or skill evaluation needs paired execution environments or orphan recovery.
hmem-release
Pre-publish checklist for hmem: skills synced, version bumped, tests green, nothing forgotten. Use before npm publish or when the user says 'release', 'publish', 'push a release', or 'neue Version'.
shipit
Turn finished work into a clean commit and pull request. Always asks first whether the commit and PR should carry AI/bot authorship attribution or stay fully human-authored, then matches the repository's existing commit conventions, splits work into logical commits, and writes a PR body with context, risk, and…