who is holding this file right now
agent-sync
Coordination plane for concurrent agents: leases with a TTL so two agents cannot claim the same work, race-free id reservation, a run journal and a generated board, over a pluggable knowledge cloud.
Install this pack on its own, or use it with the ssheleg harness.
What it ships
Each name below is an entry point an agent can be routed to.
Shape: static. Leases, ids and the journal are a fixed protocol; what varies is who holds what, which is state rather than shape.
agent-sync
Use when several coding agents work one repository at the same time and must not collide - claiming a task, reserving the next decision/question/ticket id, journaling a run, moving a cross-repo dependency, regenerating the board, or finishing work across a parent repo and its submodules - clean, pushed, and pointed at. Use it BEFORE editing any shared registry file (decisions, open questions, roadmap, workstreams, dependencies) in a project that has.claude/agent-sync.json, even when the user never mentions coordination - an unclaimed edit to those files is how two agents overwrite each other.
Install just this one
Every pack installs standalone. The whole family is one command.
npx skills add ssheleg/agent-sync
claude plugin marketplace add ssheleg/agent-sync && claude plugin install agent-sync@agent-sync
When the agent reaches for it
These are the rules the family writes into your agent's own instruction file — verbatim. Each one states the rule, the boundary in both directions, and the phrase that declines it.
/agent-sync — who is holding this file
- when: the project has agent coordination on
- decline it: no coordination
If agent-sync is installed AND .claude/agent-sync.json exists, claim shared registries BEFORE editing — decisions, open questions, roadmap, workstreams, dependencies. Reserve ids race-free and journal the run, even without a coordination request.
The boundary. NOT through it: projects without that config, ordinary code files, working alone.
Refusal phrase: "no coordination" or «без координации».
Among the routers: task-pipeline owns delivery; agent-sync file ownership when multiple agents work.
The rest of the family
super-ux v0.59.1
Scenario-driven UI development: a versioned design chain in docs/ux/ — the product vision, personas and jobs, user flows and the paid-acquisition funnel among them, a screens-and-states map with Figma frames…
task-pipeline v1.90.2
Full-cycle delivery orchestrator: an intake grill turns the request into a complete brief, then ten gated stages carry it from docs to acceptance, refusing to advance until each gate passes.
make-skill v0.29.2
A skill that builds skills: create, retrofit, audit and publish agent skills and Claude Code plugins
sheleg-design v1.64.0
The taste layer: cinematic scroll-driven landing pages (one scroll clock, motion that degrades to calm, WebGL particle formations), product-UI style packs with a ready token layer each, and the Figma border
seo-aeo-audit v0.26.3
Evidence-first website audit for search and answer engines: ten tracks from crawl access to AI citation mechanics, every finding backed by an observation and every recommendation tiered, ending in…
sheleg-dev v0.13.2
The integration layer a product reaches once it has users: Stripe subscription billing reconciled into your own database
agent-stack v0.25.5
Production patterns for AI agent systems, in four skills. The orchestrator: tool-calling loops that survive context pressure, pipelines with human checkpoints and resume, provider routing with fallback…
telegram-dev v0.2.2
Telegram, split by the API each surface actually speaks, in three skills. telegram-bots covers the official HTTP Bot API
xr-dev v0.3.2
Quest product delivery from platform choice to launch and operation, with stage owners, evidence gates and next actions.
web3d-dev v0.1.2
Realtime 3D on the web with three.js and React Three Fiber, in three skills split by the question. web3d-runtime owns how the scene runs