sync-all-repos

sync-all-repos is a skill for Claude Code, Codex from luiseiman/dotforge. It costs 39 tokens per session (4,787 once invoked), scanned D, original, MIT.

A workflow for finding GitHub-backed Git repositories on a computer and synchronizing their committed changes with the remote repository.

In plain words
What is it for?
Use it to pull or push straightforward changes, report repositories needing decisions, and review sync status across projects.
Why use it?
It helps reveal repositories that are behind, ahead, dirty, on another branch, or affected by conflicts before those states cause confusion.

Skill for Claude CodeCodex

Part of the dotforge plugin — 26 skills, 25 commands, 7 agents, 8 hooks shipped together

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.

agentmods
npx agentmods add skills/luiseiman/dotforge/sync-all-repos
Any agent
npx skills add luiseiman/dotforge --skill sync-all-repos
Clone the repo
git clone --depth 1 https://github.com/luiseiman/dotforge

Made for: Claude Code, Codex.

Or install dotforge, the plugin that ships this one along with the rest of its 26 skills, 25 commands, 7 agents, 8 hooks.

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-all-repos

README.md
[![agentmods](https://agentmods.dev/badge/skills/luiseiman/dotforge/sync-all-repos.svg)](https://agentmods.dev/skills/luiseiman/dotforge/sync-all-repos)
Your own site
<a href="https://agentmods.dev/skills/luiseiman/dotforge/sync-all-repos"><img src="https://agentmods.dev/badge/skills/luiseiman/dotforge/sync-all-repos.svg" alt="Measured on agentmods" height="20"></a>
Per session 39 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,787 The whole file, excluding the scripts and references it only reads on demand.
Security scan D 2 findings. Scan, not verified.
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 $0.00039 $0.04787
Opus 5 $0.00019 $0.02393
Sonnet 5 $0.00008 $0.00957
Haiku 4.5 $0.00004 $0.00479

Measured 5d ago against content hash d1f950499611, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade D, and why

sync-all-repos scanned grade D with 2 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 5d 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

git -C "$repo" ls-files --others --exclude-standard | grep '^\.claude/' | grep -v '^\.claude/worktrees/' | xargs -d '\n' git -C "$repo" add --

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

rm -rf "$OUTDIR"
skills/sync-all-repos/SKILL.md · 391 lines

How it starts

The opening of the file, as written. The whole thing — 391 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Sync All Repos

Discover every GitHub-backed git repo on the current machine, classify each by sync state, auto-execute the obvious cases (clean repo behind/ahead/diverged from origin), and report the ambiguous cases (uncommitted changes, non-main branches, rebase conflicts) for Claude to resolve case by case.

Use this when:

  • You sit down at the Mac or VPS and want to catch up with whatever the OTHER machine pushed to GitHub since last session
  • You're about to walk away and want to ensure all committed-but-not-pushed work is on GitHub
  • You suspect drift between machines and want a single-shot reconciliation

This skill does NOT:

  • Coordinate Mac↔VPS directly (each machine syncs with GitHub independently)
  • Auto-stash, auto-commit, or auto-resolve conflicts (Claude decides per case)
  • Touch non-GitHub repos (gitlab, bitbucket, self-hosted git all skipped)
  • Run on a timer (explicit invocation only)

Step 1: Discover repos

Search roots:

  • ~/Documents/GitHub/ (depth ≤2)
  • ~/Documents/jira nbch/ (cds-dashboard, jira-nbch)
  • ~/Documents/crm/
  • Any additional path in $DOTFORGE_DIR/registry/projects.local.yml not covered above

For each candidate directory at depth ≤2 with a .git/ subdirectory:

REMOTE=$(git -C "$dir" config --get remote.origin.url 2>/dev/null)
case "$REMOTE" in
  *github.com*) ;;
  *) continue ;;  # non-GitHub: skip silently
esac

# Opt-out marker: project declares itself out of sync scope
if [[ -f "$dir/.dotforge-sync-ignore" ]]; then
  reason=$(head -1 "$dir/.dotforge-sync-ignore" 2>/dev/null)
  reason=${reason:-"opt-out (no reason given)"}
  echo "IGNORED|$dir|$reason"
  continue
fi

echo "$dir"

Skip silently:

  • Directories without .git/
  • Repos with no origin remote
  • Repos with origin not pointing at GitHub

Skip with note (reported under "Ignored" in the final summary):

  • Repos with a .dotforge-sync-ignore file at root. The first line of that file is shown as the reason. Use this for archived projects, vendored repos, or any GitHub-backed repo you deliberately don't want auto-synced. The marker is in the project's own working tree — version-controlled by that project, not by dotforge.

Read the full file on GitHub · 391 lines

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. 5d ago First seen · 391 lines · 39 tokens per session scan D d1f950499611

Subscribe to this mod's changes

sync-all-repos is a skill published in the GitHub repository luiseiman/dotforge (8 stars, last pushed 2mo ago), licensed MIT. It adds 39 tokens to every session and 4,787 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it D with 2 findings (reads agent configuration directories, recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

scaffold

Set up or align a non-code ops/PM repo with the ops folder structure, CLAUDE.md, and INDEX.md hierarchy.

OdinMB/ops-workflow · 30 tokens

find-opps

Find new directions for an ops project — adjacent opportunities, strategic gaps, preparatory research. Use when known work is well-mined and you need to look outward.

OdinMB/ops-workflow · 37 tokens

factory-db-migration

The operational discipline for running a destructive change against a production database — schema migrations, data backfills, one-shot RPCs, historical seed imports. Adjacent to factory-data-layer.md (schema design) and factory-deployment.md (where migrations execute in CI) — this skill is about the runbook around…

nonlinear-xyz/factory-kit · 155 tokens

prioritize

Pick 2–3 independent ops tasks from active plans and backlog for autonomous execution, weighing impact, feasibility, and project goals.

OdinMB/ops-workflow · 29 tokens

factory-api

API conventions for both server actions and tRPC builds. Covers the decision between them, per-mutation Zod input schemas, central router composition, pagination shape, multi-field search via Drizzle ilike + or(), mutation lifecycle hooks, conditional query enabling, stale-time defaults, error response shape and…

nonlinear-xyz/factory-kit · 95 tokens

factory-auth

Auth and authorization conventions distilled across builds with three different auth stacks (Better Auth + orgs, Supabase Auth + RLS, Clerk). Covers the provider decision matrix, the unified wrapper interface (requireAuth / requireRole / withOrgContext), procedure tier stacking, session handling, OAuth callback…

nonlinear-xyz/factory-kit · 97 tokens