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 agentmods add skills/luiseiman/dotforge/sync-all-reposnpx skills add luiseiman/dotforge --skill sync-all-reposgit clone --depth 1 https://github.com/luiseiman/dotforgeWrote 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/luiseiman/dotforge/sync-all-repos)<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>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 | $0.00039 | $0.04787 |
| Opus 5 | $0.00019 | $0.02393 |
| Sonnet 5 | $0.00008 | $0.00957 |
| Haiku 4.5 | $0.00004 | $0.00479 |
Grade D, and why
sync-all-repos scanned grade D with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
git -C "$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" 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
$DOTFORGE_DIR/registry/projects.local.ymlnot covered above
For each candidate directory at depth ≤2 with a .git/ subdirectory:
REMOTE=$(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
originremote - Repos with
originnot pointing at GitHub
Skip with note (reported under "Ignored" in the final summary):
- Repos with a
.dotforge-sync-ignorefile 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.
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.
- 5d ago First seen · 391 lines · 39 tokens per session scan D d1f950499611
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.
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.
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.
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…
prioritize
Pick 2–3 independent ops tasks from active plans and backlog for autonomous execution, weighing impact, feasibility, and project goals.
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…
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…