sync-remote

sync-remote is a skill for Claude Code, Codex from Rezenders/scientific_writing_agent. It costs 27 tokens per session (529 once invoked), scanned A, original, Apache-2.0.

A Git workflow for safely syncing manuscript source files with a remote repository such as GitHub or Overleaf. Overleaf is an online editor for LaTeX documents, and build artifacts are generated files such as logs and temporary PDF data.

In plain words
What is it for?
Use it when pulling from or pushing to a manuscript repository. It covers checking local changes, handling conflicts, staging approved source and figure files, and using consistent commit messages.
Why use it?
It reduces conflicts and keeps generated files out of the remote project by requiring a pull before pushing and restricting which files may be staged.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

Good fit Use it when pulling from or pushing to a manuscript repository. It covers checking local changes, handling conflicts, staging approved source and figure files, and using consistent commit messages.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/rezenders/scientific_writing_agent/sync-remote
Install

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.

Any agent
npx skills add Rezenders/scientific_writing_agent --skill sync-remote
Clone the repo
git clone --depth 1 https://github.com/Rezenders/scientific_writing_agent

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for sync-remote

README.md
[![agentmods](https://agentmods.dev/badge/skills/rezenders/scientific_writing_agent/sync-remote/github.svg)](https://agentmods.dev/skills/rezenders/scientific_writing_agent/sync-remote)
Your own site
<a href="https://agentmods.dev/skills/rezenders/scientific_writing_agent/sync-remote"><img src="https://agentmods.dev/badge/skills/rezenders/scientific_writing_agent/sync-remote/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.

agentmods 80×15 button for sync-remote

Your own site · 80×15
<a href="https://agentmods.dev/skills/rezenders/scientific_writing_agent/sync-remote"><img src="https://agentmods.dev/badge/skills/rezenders/scientific_writing_agent/sync-remote.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 27 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 529 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00027 $0.00529
Opus 5.5 $0.00011 $0.00212
Sonnet 5.5 $0.00005 $0.00106
Haiku 4.5 $0.00003 $0.00053

Measured 1mo ago against content hash 232c446403a7, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

sync-remote 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.

.agents/skills/sync-remote/SKILL.md · 96 lines

What it actually says

Sync Remote

Safe git sync workflow for the scientific manuscript repository, including Overleaf-compatible constraints.

Core Rules

  • Always pull before push.
  • Never force-push.
  • Never stage build artifacts.
  • Never stage generated manuscript PDFs from the repository root or build/.
  • Stop and ask the user if pull conflicts occur.

Allowed Staged Content

Stage only manuscript source files and intentional assets such as:

  • *.tex
  • *.bib
  • *.cls
  • *.sty
  • *.bst
  • figure assets such as *.png, *.svg, *.eps, and figure *.pdf
  • .gitignore

If unsure whether a file is a source asset or a generated artifact, ask before staging it.

Never Stage

  • *.aux
  • *.log
  • *.out
  • *.fls
  • *.fdb_latexmk
  • *.synctex.gz
  • generated manuscript PDFs
  • _minted-* caches
  • unrelated workspace files such as COLCON_IGNORE

Pull Workflow

cd <PROJECT_ROOT>
git status

If git status shows local changes, stop and ask the user whether to commit, stash, or postpone the sync. Do not choose on the user's behalf.

Only pull when the worktree is clean:

git pull origin main

If git pull reports conflicts:

  1. Stop.
  2. Report the conflicting files.
  3. Ask the user how to proceed.

Push Workflow

cd <PROJECT_ROOT>
git status
test -z "$(git status --short)" || exit 1  # clean worktree required before pull
git pull origin main
git add -- <MAIN_TEX> <SECTION_FILE>
git diff --cached --name-only
git commit -m "Edit: scope - short description"
git push origin main

Stage explicit paths that actually exist instead of broad globs. Replace <SECTION_FILE> with the real files you intend to sync. This avoids accidental staging and works even when optional directories or file patterns are absent.

Commit Message Pattern

Use:

<verb>: <section or scope> - <short description>

Preferred verbs:

  • Edit
  • Add
  • Fix
  • Remove
  • Rewrite
  • Restructure
Changes

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.

  1. 1mo ago Changed · +6 lines · -29 tokens per session 232c446403a7
  2. 2mo ago First seen · 90 lines · 56 tokens per session scan A b17f3731fa0a

Subscribe to this mod's changes

sync-remote is a skill published in the GitHub repository Rezenders/scientific_writing_agent (14 stars, last pushed 17d ago), licensed Apache-2.0. It adds 27 tokens to every session and 529 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.

Related

sync-remote compared with skills from other repositories

sync-remote next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
sync-remoteRezenders/scientific_writing_agentSkill1417d agoApache-2.0A27Claude Code, Codex
merge-batchdiegosouzapw/OmniRouteSkill83k6d agoMITA46Claude Code
prowler-commitprowler-cloud/prowlerSkill15kyesterdayApache-2.0A44Claude Code, Codex
gh-auth-isolationgithub/gh-awSkill5.6kyesterdayMITA20Claude Code, Codex
github-skillzeenie-ai/OpenCompanySkill1.1kyesterdayMITA51Claude Code
comet-githubrpamis/cometSkill3.3kyesterdayMITA72Claude Code, Codex
release-helperSahir619/fable-methodSkill2.3k1mo agoMITA43Claude Code