upstream-sync

upstream-sync is a skill for Claude Code, Codex from acaprino/daodan. It costs 155 tokens per session (3,204 once invoked), scanned A, original, MIT.

A maintenance guide for plugins copied from other code repositories, including how to compare local files with their upstream versions.

In plain words
What is it for?
Use it when checking upstream updates, classifying file differences, fetching repository content, and merging selected changes.
Why use it?
It reduces the risk of overwriting useful local changes or missing important updates from the original repository.

Skill for Claude CodeCodex

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/acaprino/daodan/upstream-sync
Any agent
npx skills add acaprino/daodan --skill upstream-sync
Clone the repo
git clone --depth 1 https://github.com/acaprino/daodan

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 upstream-sync

README.md
[![agentmods](https://agentmods.dev/badge/skills/acaprino/daodan/upstream-sync.svg)](https://agentmods.dev/skills/acaprino/daodan/upstream-sync)
Your own site
<a href="https://agentmods.dev/skills/acaprino/daodan/upstream-sync"><img src="https://agentmods.dev/badge/skills/acaprino/daodan/upstream-sync.svg" alt="Measured on agentmods" height="20"></a>
Per session 155 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,204 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00155 $0.03204
Opus 5 $0.00077 $0.01602
Sonnet 5 $0.00031 $0.00641
Haiku 4.5 $0.00015 $0.00320

Measured 5d ago against content hash 40d069f7a6d5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

upstream-sync scanned grade A with 1 finding 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.

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

- `render-graphs.js` was converted to ESM upstream, which is correct there (`"type": "module"` in the upstream `package.json`) and broken here: the export ships no `package.json` next to it, so `.js` is CommonJS and `imp
.agents/skills/upstream-sync/SKILL.md · 95 lines

How it starts

The opening of the file, as written. The whole thing — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Upstream-synced plugins

Some plugins are ported from external repositories and should be kept in sync with their upstream source. When asked to update one of these plugins, fetch the latest content from the upstream URL using gh api and apply any changes, then follow the standard marketplace update workflow in AGENTS.md.

Nothing listed under "Deliberately not vendored" in AGENTS.md belongs in the table below. Those areas were removed and delegated on purpose; do not add rows for them on a future pass. The former obra/superpowers export row was retired with the VS Code extension and stays retired.

Default upstream-update strategy

When the user asks for "upstream updates" (or similar), this is the default workflow. Do not blindly overwrite local files - most syncs need targeted merging because local has legitimate customizations.

  1. Check all synced plugins in parallel. For each file in the sync table below, diff the upstream against the local version. Spawn Explore agents when there are many files to parallelize the diffing. Focus the reports on: which files differ, what changed, and whether the drift is intentional or worth pulling.

  2. Classify each file before touching it:

    • Clear win - new upstream file missing locally, or a bug/fact fix with no local conflict. Pull directly.
    • Minor refinement - small wording/metadata changes. Pull if no local frontmatter or content conflicts.
    • Hard merge - upstream rewrote a section we also evolved locally. Layer upstream changes onto local; do not overwrite.
    • Intentional drift (do not touch) - local namespace rewrites (upstream <their-plugin>: -> local <our-plugin>:), local polish (typo fixes, expanded triggers), style conventions (no dash-aside construct per AGENTS.md; no emojis in some plugins), local-only additions (custom presets, Ecosystem Integration sections), upstream dash-asides rewritten to sentences/parens/colons.
  3. Preserve these local customizations on every merge:

    • Source attribution lines at the top of files
    • Frontmatter: localized description (often multiline with >), tools, color, version, model
    • Plugin-specific style: no dash-aside construct (rewrite "X — Y — Z" / "X -- Y -- Z" / "X - Y - Z" asides into sentences, parens, or colons), no emojis in some plugins
    • Namespace replacements (upstream <their-plugin>:X -> local <our-plugin>:X)
    • Local-only sections (e.g., ## Ecosystem Integration blocks added during earlier syncs)

Read the full file on GitHub · 95 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 · 95 lines · 155 tokens per session scan A 40d069f7a6d5

Subscribe to this mod's changes

upstream-sync is a skill published in the GitHub repository acaprino/daodan (8 stars, last pushed today), licensed MIT. It adds 155 tokens to every session and 3,204 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). 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

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

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens