A tool for synchronizing locally stored third-party coding skills with their upstream repositories, the original online projects they came from. It reapplies local patches and reports new or changed skills.

Updating vendored skills in a dotfiles source checkout, preserving patches, and reviewing upstream changes before committing them.

It helps keep copied skills current without losing deliberate local changes. It also highlights conflicts, removed files, and missing upstream paths.

sync-skills — Skill for Claude Code and Codex by jkomyno

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 jkomyno/.dotfiles --skill sync-skills

Clone the repo

git clone --depth 1 https://github.com/jkomyno/.dotfiles

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/jkomyno/.dotfiles/sync-skills/github.svg)](https://agentmods.dev/skills/jkomyno/.dotfiles/sync-skills)

Your own site

<a href="https://agentmods.dev/skills/jkomyno/.dotfiles/sync-skills"><img src="https://agentmods.dev/badge/skills/jkomyno/.dotfiles/sync-skills/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/jkomyno/.dotfiles/sync-skills"><img src="https://agentmods.dev/badge/skills/jkomyno/.dotfiles/sync-skills.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 35 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,346 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.

Model	Per session	Once invoked
Fable 5.1	$0.00035	$0.01346
Opus 5	$0.00017	$0.00673
Sonnet 5	$0.00007	$0.00269
Haiku 4.5	$0.00003	$0.00135

Measured 11d ago against content hash 30085539ee3a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

sync-skills 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.

The scan reads SKILL.md. This mod also ships 4 executable files (scripts/apply-frontmatter-overrides.py, scripts/apply-upstream.sh, scripts/make-patch.sh, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

target/home/.agents/skills/sync-skills/SKILL.md · 97 lines

How it starts

The opening of the file, as written. The whole thing — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Sync Vendored Skills

Third-party skills are vendored into the dotfiles repository under target/home/.agents/skills/<name>/ and deployed by mise to ~/.agents/skills/<name>/. manifest.json in this skill's directory maps each vendored skill to its upstream repository and in-repo path. This skill keeps the vendored copies in sync with upstream while preserving deliberate local modifications as patch files.

Inspired by dmmulroy's sync-pocock-skills, generalized to many upstreams.

Quick start

Always operate on the dotfiles source checkout, never on the deployed ~/.agents/skills, so accepted changes land in git:

DOTFILES="${DOTFILES:-$HOME/work/me/dotfiles}"
SYNC_ROOT="$DOTFILES/target/home/.agents/skills/sync-skills"
bash "$SYNC_ROOT/scripts/sync.sh" --keep-upstream

Workflow

1. Analyse

Run sync.sh as above and parse the output sections:

UPSTREAM_CHANGES — per-skill list of files that differ from upstream-plus-our-patches. Annotations: (changed, no patch), (upstream changed, has patch), (patch conflict), (new file upstream), (removed upstream).
MISSING_UPSTREAM — a manifest entry whose path no longer exists upstream; the repo restructured. Locate the skill's new path in the retained clone and update manifest.json.
NEW_SKILLS — skills available in repos we already track but do not vendor. Ask the user which to add; append rejected ones to patches/excluded.txt.
UNPATCHED_PATTERNS — host-specific wording in vendored skills that is not covered by a patch. Review each hit and either make a patch or add a deliberate exclusion comment near the text.
UPSTREAM_DIRS — retained clone paths (with --keep-upstream) for reading upstream files.

2. Apply upstream changes

For each CHANGED: entry:

(changed, no patch) / (new file upstream) — safe to take upstream. Run:

bash "$SYNC_ROOT/scripts/apply-upstream.sh" <skill_name> <upstream_skill_dir>

(upstream changed, has patch) — apply-upstream.sh copies upstream and re-applies the stored patch automatically. If it prints PATCH_CONFLICT, read both versions, resolve in the vendored copy, then regenerate the patch with make-patch.sh.
(patch conflict) — same manual resolution: read upstream and ours, merge, regenerate the patch.
(removed upstream) — flag to the user; suggest deleting the file or the whole skill (and its manifest entry).

Read the full file on GitHub · 97 lines

Files

What ships with it

11 files 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.

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.

11d ago First seen · 97 lines · 35 tokens per session scan A 30085539ee3a

Subscribe to this mod's changes

sync-skills is a skill published in the GitHub repository jkomyno/.dotfiles (5 stars, last pushed 6d ago), licensed MIT. It adds 35 tokens to every session and 1,346 once invoked, about $0.0002 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 2026-08-31.

Building agents

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens