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 instructions/powersync-ja/agent-skills/agents-mdgit 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 | $0.00286 | $0.00286 |
| Opus 5 | $0.00143 | $0.00143 |
| Sonnet 5 | $0.00057 | $0.00057 |
| Haiku 4.5 | $0.00029 | $0.00029 |
Grade A, and why
agent-skills AGENTS.md 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.
What it actually says
PowerSync Agent Skills
If you are building or modifying anything that uses PowerSync, you must follow the playbook in skills/powersync/AGENTS.md — not a condensed summary.
That file includes:
- Agent compliance (non-negotiable): ask Cloud vs self-hosted, ask backend if unspecified, CLI-first, no silent shortcuts.
- Full onboarding sequence, setup paths, SDK references, and debugging.
Do not assume Supabase, assume self-hosted Docker, or skip CLI steps unless the user explicitly opts out.
powersync login is PowerSync Cloud only. Self-hosted does not use it — see skills/powersync/references/powersync-cli.md § “Authentication”.
When editing files under skills/powersync/, preserve and strengthen playbook language so agents cannot reasonably treat references as optional recipes.
Verifying changes
After changing any file under skills/, you must verify the skill still passes Snyk's security scanner (snyk-agent-scan) before considering the work done. Run the scan as described in "Verifying changes with snyk-agent-scan" in README.md and confirm it reports zero issues. Also run node scripts/validate.mjs, which CI enforces.
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 · 19 lines · 286 tokens per session scan A e517b5f71d2a
agent-skills AGENTS.md is an instructions file published in the GitHub repository powersync-ja/agent-skills (18 stars, last pushed 7d ago), licensed MIT. It adds 286 tokens to every session, about $0.0014 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 instructions, from other repositories
syncular AGENTS.md
Instructions for syncular/syncular, covering syncular agent instructions, doctrine (enforced), coding rules, prose rules for docs and voice.
anytype-ts AGENTS.md
AGENTS.md instructions for anyproto/anytype-ts, covering agents.md, project structure, state management with mobx, electron integration and inter-process communication (ipc).
mdread CLAUDE.md
Instructions for techjewel/mdread, covering claude.md, what this is, commands, architecture and styles (scss).
anytype-ts CLAUDE.md
Claude Code instructions for anyproto/anytype-ts, covering claude.md, development commands, core commands, testing and quality and distribution.
PowerScroll CLAUDE.md
Claude Code instructions for CynaCons/PowerScroll, covering powerscroll — claude instructions, project overview, tech stack, critical workflow: handling user feedback and plan.md format (strict).
siyuan AGENTS.md
AGENTS.md instructions for siyuan-note/siyuan, covering agents.md, 1. non-negotiable constraints, do not hand-edit, verification and prohibited operations and 2. project-specific rules.