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/claude-mdgit clone --depth 1 https://github.com/powersync-ja/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/instructions/powersync-ja/agent-skills/claude-md)<a href="https://agentmods.dev/instructions/powersync-ja/agent-skills/claude-md"><img src="https://agentmods.dev/badge/instructions/powersync-ja/agent-skills/claude-md.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00186 | $0.00186 |
| Opus 5 | $0.00093 | $0.00093 |
| Sonnet 5 | $0.00037 | $0.00037 |
| Haiku 4.5 | $0.00019 | $0.00019 |
Grade A, and why
agent-skills CLAUDE.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 5d 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
See AGENTS.md for guidance. For PowerSync work, follow skills/powersync/AGENTS.md in full — including Agent compliance. powersync login = PowerSync Cloud only.
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. The usual false-positive triggers are user:password@ connection strings, hex strings of 20+ characters (commit SHAs, realistic example IDs), literal credential values, and wording that reads as credential harvesting. That README section lists the safe alternatives for each.
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.
- 5d ago First seen · 6 lines · 186 tokens per session scan A 4d34e23adecf
agent-skills CLAUDE.md is an instructions file published in the GitHub repository powersync-ja/agent-skills (18 stars, last pushed yesterday), licensed MIT. It adds 186 tokens to every session, about $0.0009 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).
PowerScroll AGENTS.md
AGENTS.md instructions for CynaCons/PowerScroll: Read CLAUDE.md first — it is the canonical project guide (stack, patterns, testing rules, showcase rules). The rules below are the ones sub-agents most often get wrong.