aistack-sync

aistack-sync is a skill for Claude Code, Codex from alp82/aistack. It costs 56 tokens per session (505 once invoked), scanned A, original, MIT.

A workflow for publishing a measured snapshot of Claude Code usage from this computer to an aistack account.

In plain words
What is it for?
Use it when you ask to sync your stack, publish your usage, or update the measured layer of your stack.
Why use it?
It gives you a review step and requires your confirmation before usage data is published.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions Claude Code.

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/alp82/aistack/aistack-sync
Any agent
npx skills add alp82/aistack --skill aistack-sync
Clone the repo
git clone --depth 1 https://github.com/alp82/aistack

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 aistack-sync

README.md
[![agentmods](https://agentmods.dev/badge/skills/alp82/aistack/aistack-sync.svg)](https://agentmods.dev/skills/alp82/aistack/aistack-sync)
Your own site
<a href="https://agentmods.dev/skills/alp82/aistack/aistack-sync"><img src="https://agentmods.dev/badge/skills/alp82/aistack/aistack-sync.svg" alt="Measured on agentmods" height="20"></a>
Per session 56 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 505 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 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 5.1 $0.00056 $0.00505
Opus 5 $0.00028 $0.00253
Sonnet 5 $0.00011 $0.00101
Haiku 4.5 $0.00006 $0.00051

Measured 6d ago against content hash 0230b7b2dc6a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

aistack-sync 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 6d 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.

packages/cli/skills/aistack-sync/SKILL.md · 49 lines

What it actually says

aistack sync

Publish the local measured-usage snapshot to the user's aistack stack. The aistack MCP server does all the work: it scans the transcripts on this machine, stages the exact bytes, and gates the send behind a dialog only the user can answer. You trigger and display. You never decide.

Steps

  1. Call the sync_preview tool on the aistack MCP server. No arguments.
  2. Show the returned text to the user verbatim, in a code block. Do not summarize it. Do not omit lines. Do not add numbers of your own.
  3. If the output says publish unavailable, stop and relay the reason.
  4. If the user asked for a sync, call sync_publish with the preview id from the output. A confirmation dialog appears. The user answers it themselves. Wait; the dialog can take minutes.
  5. Relay the tool result verbatim. "Not published" is a valid outcome, not an error to work around.

Rules

  • Never call sync_publish without a sync_preview in the same conversation.
  • Never replace the preview text with your own summary. The preview is the review surface the user consents on.
  • A cancel or a timeout is the user's answer. Do not raise the gate again in the same turn. Retry only when the user asks.
  • If the aistack MCP server is not connected, say so and point at the setup step below. Do not publish through any other channel. There is none.

Setup (one time, done by the user)

npx @use-aistack/cli connect claude

That installs both halves: the aistack MCP server (user scope) and this Skill. Manual alternative:

claude mcp add --scope user aistack -- npx -y @use-aistack/cli mcp

The machine must be linked once with npx @use-aistack/cli login.

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. 6d ago First seen · 49 lines · 56 tokens per session scan A 0230b7b2dc6a

Subscribe to this mod's changes

aistack-sync is a skill published in the GitHub repository alp82/aistack (46 stars, last pushed 3d ago), licensed MIT. It adds 56 tokens to every session and 505 once invoked, about $0.0003 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 2026-08-30.

Related

Other skills, from other repositories