Borrowing it
Nothing to install: this file belongs to kamiazya/whiteboard. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/kamiazya/whiteboard/main/.claude/skills/loro-crdt-usage/SKILL.mdgit clone --depth 1 https://github.com/kamiazya/whiteboardWrote 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/kamiazya/whiteboard/loro-crdt-usage)<a href="https://agentmods.dev/skills/kamiazya/whiteboard/loro-crdt-usage"><img src="https://agentmods.dev/badge/skills/kamiazya/whiteboard/loro-crdt-usage/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/kamiazya/whiteboard/loro-crdt-usage"><img src="https://agentmods.dev/badge/skills/kamiazya/whiteboard/loro-crdt-usage.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 | $0.00092 | $0.02104 |
| Opus 5 | $0.00046 | $0.01052 |
| Sonnet 5 | $0.00018 | $0.00421 |
| Haiku 4.5 | $0.00009 | $0.00210 |
Grade A, and why
loro-crdt-usage 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 3d 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.
How it starts
The opening of the file, as written. The whole thing — 163 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Using loro-crdt in this repo
Loro is where this project's data actually lives, and its failure mode is the worst kind: a wrong container choice loses data with no conflict, no error, and both replicas agreeing on the truncated result. Nothing goes red. The loss is found, if ever, by a person noticing their reply is gone.
So the rule here is the repo's rule everywhere else, sharpened: a claim
about Loro is worth what its measurement is worth. The version is pinned
in pnpm-workspace.yaml (loro-crdt: "1.13.6"), the API has changed
under this repo more than once, and loro.dev is not reachable from this
environment anyway. What IS reachable and authoritative is shipped inside
the package — see "Where the answers actually are" below.
The rule: a lazily-created child container must be mergeable
map.getOrCreateContainer(key, new LoroMap()) mints a regular op-id
child. Two replicas that each open the same key having never seen the
other's end up with two containers, and the map's conflict resolution keeps
one and hides the other.
Measured on 1.13.6 — two peers, no common ancestor for the key, each writing one entry:
| opened with | both replicas read |
|---|---|
getOrCreateContainer |
{"fromB": "reply B"} |
ensureMergeableMap |
{"fromA": "reply A", "fromB": "reply B"} |
Same for ensureMergeableText ("ab" vs "b") and
ensureMergeableMovableList (["A","B"] vs ["B"]).
loro-crdt says so itself. 1.13.0's changelog: "getOrCreateContainer is
deprecated for lazy map-child creation; migrate those call sites to
ensureMergeable*." A mergeable child lives at a deterministic
ContainerID derived from (parent, key, kind), so the two peers were
editing one container all along.
Use openMergeableMap / openMergeableText /
openMergeableMovableList from
packages/loro-adapter/src/mergeable-containers.ts, never the raw
method. Four things the helper exists for, each measured:
ensureMergeable*THROWS on a key that already holds a non-mergeable value —Cannot create a mergeable Map at key "k": the key already holds a non-mergeable value. That is every document written before the helper landed, so a bare swap breaks stored data. The helper takes the mergeable branch only for an ABSENT key and leaves an occupied one exactly as it was, which is what makes this safe with no migration.- They live on
LoroMapalone. Not onLoroList,LoroMovableListorLoroTree— which is the shape of the problem, not an omission: a list position is already a unique op, so only a map KEY needs two peers to agree on which child it names. - A mixed pair still loses one side. One replica opening the key the old way while another opens it mergeable converges on the mergeable one. The fix removes the hazard for containers created from here on; it cannot repair a fork that already happened.
getOrCreateContainerreading a containerensureMergeable*created is fine, so a reader on an older code path is not broken by the switch.
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.
- 3d ago First seen · 163 lines · 92 tokens per session scan A 1fb9e28820f7
loro-crdt-usage is a skill published in the GitHub repository kamiazya/whiteboard (6 stars, last pushed today), licensed Apache-2.0. It adds 92 tokens to every session and 2,104 once invoked, about $0.0005 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 2026-09-06.
Other skills, from other repositories
create-pr
Creates a GitHub PR with a Linear-ticket-prefixed title and a decision-led, narrative description for prisma-next. Use when the user wants to create a pull request, open a PR, or submit changes for review.
schema-exploration
Lists tables, describes columns and data types, identifies foreign key relationships, and maps entity relationships in a database. Use when the user asks about database schema, table structure, column types, what tables exist, ERD, foreign keys, or how entities relate.
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…
supabase
Supabase / PostgREST Row-Level-Security playbook — pull the anon (or leaked servicerole) key out of the frontend JS, map tables from the auto-generated OpenAPI spec, test anonymous RLS READ disclosures (PII/secret leaks), and anonymous RLS WRITE abuse (insert/update/delete — e.g. forging…
nornicdb-cypher-queries
Pick fast, predictable Cypher query shapes in NornicDB — point lookups, batch retrieval, pagination, search, traversal, batched UNWIND/MERGE writes, cleanup, multi-tenant isolation. Use when writing or reviewing Cypher whose latency or throughput matters; maps user intent to the executor's hot-path query templates.
dsql
Build with Aurora DSQL — manage schemas, execute queries, handle migrations, diagnose query plans, diagnose cluster performance, load data, and develop applications with a serverless, distributed SQL database. Covers IAM auth, multi-tenant patterns, MySQL-to-DSQL and PostgreSQL-to-DSQL schema conversion, foreign key…