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 skills add j4flmao/agent-skills --skill crdtsgit clone --depth 1 https://github.com/j4flmao/agent-skillsWrote 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/j4flmao/agent-skills/crdts)<a href="https://agentmods.dev/skills/j4flmao/agent-skills/crdts"><img src="https://agentmods.dev/badge/skills/j4flmao/agent-skills/crdts/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.
<a href="https://agentmods.dev/skills/j4flmao/agent-skills/crdts"><img src="https://agentmods.dev/badge/skills/j4flmao/agent-skills/crdts.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00144 | $0.02133 |
| Opus 5.5 | $0.00058 | $0.00853 |
| Sonnet 5.5 | $0.00029 | $0.00427 |
| Haiku 4.5 | $0.00014 | $0.00213 |
Grade A, and why
architecture-crdts 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 today.
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.
How it starts
The opening of the file, as written. The whole thing — 167 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Conflict-free Replicated Data Types (CRDTs)
Purpose
CRDTs let replicas accept writes independently (offline, peer-to-peer, multi-region) and still converge to the same state once they have seen the same updates, with no central lock or transform server. They trade some storage and semantic control for availability and simple sync. Use proven libraries; design the document model, sync transport, persistence, and access control around them.
Agent Protocol
Trigger
"CRDT", "collaborative editor", "multiplayer editing", "Yjs", "Automerge", "Loro", "local-first", "offline merge", "OT vs CRDT", "conflict resolution without server".
Input Context
- Data shape (text, rich text, lists, maps, counters, trees/canvas).
- Concurrency: number of simultaneous editors, offline duration.
- Topology: client-server relay, peer-to-peer, multi-region servers.
- Auth model and audit/history requirements.
Output Artifact
CRDT design: per-field type, library choice, sync/persistence architecture, compaction and auth plan.
Response Format
Document model: {field: CRDT type}
Library: {Yjs|Automerge|Loro} Transport: {WebSocket relay|WebRTC|HTTP sync}
Persistence: {updates log + snapshots} Compaction: {policy}
Auth: {room-level|server-validated updates}
Semantics caveats: {e.g. LWW on title, interleaving}
Completion Criteria
- Each field's merge semantics stated (what happens on concurrent edits).
- Server validates who may write which document.
- Persistence keeps update log + periodic snapshots; growth bounded.
- Convergence tested with randomized concurrent operations.
Two Families
| Family | Replicas exchange | Requirement on merge/delivery |
|---|---|---|
| State-based (CvRDT) | Whole state (or deltas) | Merge is commutative, associative, idempotent (a join-semilattice); any delivery order, duplicates OK |
| Operation-based (CmRDT) | Operations | Concurrent ops commute; delivery exactly-once and causally ordered (usually provided by the library's sync protocol) |
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.
- today Changed · +138 lines · +144 tokens per session 41912558526b
- 1mo ago First seen · 29 lines · 0 tokens per session scan A fe84b3213e09
architecture-crdts is a skill published in the GitHub repository j4flmao/agent-skills (34 stars, last pushed today), licensed MIT. It adds 144 tokens to every session and 2,133 once invoked, about $0.0006 per session on Opus 5.5. 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 2026-09-05.
Other skills, from other repositories
task-planning
Use when work spans multiple steps, phases, or sessions, when resuming a task started earlier, when the user asks for a plan/roadmap/progress tracking, or when they use the /dxos:project command (any verb — list, tasks, new, end, track, hydrate, resume). Covers the project registry, maintaining a durable TASKS.md +…
drawing
Draw architecture, data-flow, class and dependency diagrams as SVG with the drawing CLI (drawing.sh, npm package @dxos/drawing). You write a short text file saying which boxes exist and how they relate; the CLI places the boxes on a grid, routes every arrow, reports crossings and bends, and writes an SVG. Use when…
mflow
Use when working in a repo that uses mflow, coordinating multiple AI agents/worktrees, setting up mflow sync, installing mflow MCP in Codex/Claude Code/Cursor/opencode, or before git operations where synced file changes may affect commits. Applies to CLI, MCP, room secrets, pause/resume, locks, status checks, and safe…
risk-storming-facilitator
Plan and facilitate collaborative risk storming sessions for architecture teams. Use this skill whenever the user wants to run a risk identification workshop, organize a risk storming exercise, plan a collaborative risk assessment session, facilitate architecture risk discovery with a team, prepare a risk workshop…
writing-specs
Use when writing or editing a spec inside a Pairdown room — a document a team will read without you in the room. Covers where to think out loud versus what belongs in the document, and the rules that keep the document skimmable.
joining-a-room
Use when the user wants to join, open, create or leave a Pairdown room, when they mention a room id or a Pairdown link, when they ask what rooms exist, or when they ask why an agent is not showing up in a room. Covers attaching a session to a room, how being summoned works, and the two things that usually go wrong.