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 agentmods add skills/powersync-ja/agent-skills/powersyncnpx skills add powersync-ja/agent-skills --skill powersyncgit clone --depth 1 https://github.com/powersync-ja/agent-skillsWhat 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 | $0.00118 | $0.01483 |
| Opus 5 | $0.00059 | $0.00741 |
| Sonnet 5 | $0.00024 | $0.00297 |
| Haiku 4.5 | $0.00012 | $0.00148 |
Grade A, and why
powersync 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 2d 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 — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PowerSync Skills
Use this skill to onboard a project onto PowerSync without trial-and-error. Treat this as a guided workflow first and a reference library second.
Agents: Read AGENTS.md before proceeding. It contains the mandatory compliance rules and onboarding playbook. The Quick Rules below are a reminder, not a substitute. powersync login is PowerSync Cloud only (PAT); self-hosted does not use it.
Terminology
- Operator — the human directing this agent (whose request you are fulfilling).
- User — an end-user of the operator's PowerSync app (JWT subjects, the row a sync stream filters by, the person calling
disconnectAndClear()).
If a sentence is ambiguous, default to the operator interpretation. Full legend in AGENTS.md.
Quick Rules
- CLI-first. Use the PowerSync CLI for all operations. Do not hand-write config files. See
references/powersync-cli.md. - Ask, don't assume. Ask the operator: Cloud vs self-hosted, and which backend (Supabase, Postgres, MongoDB, MySQL, MSSQL). Do not default to Supabase.
- Backend before frontend. Deploy sync config and verify the service before writing app code.
- Sync Streams for new projects. Sync Rules are legacy.
- Keep credentials in
.env, never hardcoded. Record URLs and keys in.envas they become available; config (!env) and app code read from there. - Default scope on existing projects: sync-config only. Do not edit
service.yamlorcli.yamlunless the operator explicitly authorized service/infra changes in this conversation. - Confirm the target instance before any mutating command (
deploy,destroy,stop,link --create,pull instance). Never deploy to an instance not authorized by the operator. Treat production as off-limits unless explicitly approved. - Use project memory. If your harness supports it, persist the CLI invocation, sync-config path, authorized instance ids + environment (dev/staging/prod), and allowed scope of changes. Verify saved values still match reality before acting on them. See
AGENTS.md§ "Continuous Use & Guardrails".
What ships with it
27 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- AGENTS.md 14 KB
- CLAUDE.md 41 B
- references/attachments.md 15 KB
- references/custom-backend.md 14 KB
- references/migration-from-electric.md 5.7 KB
- references/onboarding-custom.md 6.1 KB
- references/onboarding-supabase.md 5.5 KB
- references/powersync-cli.md 28 KB
- references/powersync-debug.md 21 KB
- references/powersync-overview.md 3.8 KB
- references/powersync-service.md 29 KB
- references/raw-tables.md 9.7 KB
- references/sdks/powersync-dart.md 8.4 KB
- references/sdks/powersync-dotnet.md 20 KB
- references/sdks/powersync-js-node.md 7.0 KB
- references/sdks/powersync-js-orm.md 3.0 KB
- references/sdks/powersync-js-react-native.md 6.0 KB
- references/sdks/powersync-js-react.md 11 KB
- references/sdks/powersync-js-tanstack.md 9.6 KB
- references/sdks/powersync-js-vue.md 9.8 KB
- references/sdks/powersync-js.md 37 KB
- references/sdks/powersync-kotlin.md 16 KB
- references/sdks/powersync-swift.md 12 KB
- references/sqlite-extensions.md 7.4 KB
- references/supabase-auth.md 18 KB
- references/sync-config.md 27 KB
- references/terraform.md 5.6 KB
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.
- 2d ago First seen · 86 lines · 118 tokens per session scan A c1cda66afb04
powersync is a skill published in the GitHub repository powersync-ja/agent-skills (18 stars, last pushed 7d ago), licensed MIT. It adds 118 tokens to every session and 1,483 once invoked, about $0.0006 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.
Other skills, from other repositories
html-design
Create, redesign, repair, validate, preview, and package lightweight standalone web apps as portable HTML. Use for single-file browser tools, calculators, converters, dashboards, guided workflows, knowledge interfaces, touch-friendly mini-games, full-screen HTML presentations, reusable presentation brand packs, and…
sqlite-schema-design
Design or review schemas for crates/cloudsync using SQLite Sync constraints, not generic SQLite advice. Use when adding synced tables, changing synced columns, or planning CloudSync-safe migrations.
reactive-sqlite-ui
Build SQLite-backed reactive UI in apps/desktop using stable patterns for reads, selection, forms, writes, and loading states. Use when implementing or reviewing screens built on useDrizzleLiveQuery and SQLite mutations.
migrate-to-sqlite
Migrate a TinyBase table to SQLite. Use when asked to move a data domain (e.g. templates, vocabs) from the TinyBase store to the app SQLite database.
lark-base
【何时用:仅当用户明确指向飞书/Lark(发到飞书、飞书文档等)时使用;泛指做个文档或PPT或表格或方案默认走本地工具,不要误用飞书】飞书多维表格（Base）操作：建表、字段、记录、视图、统计、公式/lookup、表单、仪表盘、应用模式（BaseApp/AppMode 页面与组件）、Workspace 目录、workflow、角色权限；遇到 Base/多维表格/bitable、BaseApp/AppMode 或 /app/ 链接时使用。BaseApp 不走 lark-apps；文件导入转 lark-drive，认证/授权转 lark-shared。.
meridian-etl
Debug and work with Meridian's ETL pipeline. Covers session boundary detection, cursor management, DB queries, and common failure modes.