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/cynacons/powerscroll/agents-mdgit clone --depth 1 https://github.com/CynaCons/PowerScrollWrote 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/cynacons/powerscroll/agents-md)<a href="https://agentmods.dev/instructions/cynacons/powerscroll/agents-md"><img src="https://agentmods.dev/badge/instructions/cynacons/powerscroll/agents-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 | $0.00374 | $0.00374 |
| Opus 5 | $0.00187 | $0.00187 |
| Sonnet 5 | $0.00075 | $0.00075 |
| Haiku 4.5 | $0.00037 | $0.00037 |
Grade A, and why
PowerScroll 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 yesterday.
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
Agent instructions (Codex, Grok, Gemini and other CLI agents)
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.
- Tests: Playwright E2E only, in
tests/<feature>/NN-name.spec.ts. Test numbers are globally unique across the whole project (check the highest existing number before adding one). Each spec header saysCovers: REQ-XXX-NNN. - Requirements: every user-visible behaviour has a
REQ-<AREA>-NNNrow indocs/SRS_<AREA>.mdwith the covering test in the last column. - Verification before you report:
npm run typecheck,npm run lint, thennpx playwright test(full suite, ~3–5 min, starts its own Vite on port 5193). Never enable retries. Report exact pass/fail counts. - Driving the canvas in tests: synthetic mouse events do not reach Konva.
Use pointer events dispatched on the stage container, or set state through
window.__POWERNOTE_STORES__/window.__POWERNOTE_BRIDGE__. Look attests/helpers.tsand an existing spec in the same folder first. - Do not commit, tag, bump versions, or edit
PLAN.mdunless your task explicitly says so. The coordinator owns those. - Style: simplicity over completeness. Small, readable diffs. No new dependencies unless the task names them.
- Finish with a short summary: files changed, decisions taken, exact test numbers, anything left undone.
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.
- yesterday First seen · 25 lines · 374 tokens per session scan A 7923f6e90172
PowerScroll AGENTS.md is an instructions file published in the GitHub repository CynaCons/PowerScroll (0 stars, last pushed yesterday), licensed MIT. It adds 374 tokens to every session, about $0.0019 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 2026-09-04.
Other instructions, from other repositories
syncular AGENTS.md
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).
agent-skills AGENTS.md
AGENTS.md instructions for powersync-ja/agent-skills, covering powersync agent skills and verifying changes.
agent-skills CLAUDE.md
Claude Code instructions for powersync-ja/agent-skills: See AGENTS.md for guidance. For PowerSync work, follow skills/powersync/AGENTS.md in full — including Agent compliance. powersync login = PowerSync Cloud only.
ndb-core e2e-tests.instructions.md
Instructions for Aam-Digital/ndb-core, covering e2e testing patterns (playwright), imports, loading the app, test data generators and clock and dates.