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/claude-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/claude-md)<a href="https://agentmods.dev/instructions/cynacons/powerscroll/claude-md"><img src="https://agentmods.dev/badge/instructions/cynacons/powerscroll/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 | $0.01696 | $0.01696 |
| Opus 5 | $0.00848 | $0.00848 |
| Sonnet 5 | $0.00339 | $0.00339 |
| Haiku 4.5 | $0.00170 | $0.00170 |
Grade A, and why
PowerScroll 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 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 — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PowerScroll — Claude Instructions
Project Overview
PowerScroll (formerly PowerNote) is an offline-first, file-based visual note-taking app combining OneNote structure, a presentation canvas, and whiteboard freedom. Built with React 18 + TypeScript + Vite + Konva.js + Zustand.
Tech Stack
- Canvas: Konva.js (react-konva) — MIT license, chosen over tldraw ($6K/year)
- State: 9 Zustand stores (workspace, canvas, draw, tool, group, bridge, diagram, editor, fileBinding)
- Text: Markdown rendering via
marked, raw editing in textarea overlay - Testing: Playwright E2E, ASPICE-style SRS docs with traceability
Critical Workflow: Handling User Feedback
When the user gives feedback, bug reports, or feature requests — ALWAYS do these 3 things before writing code:
- Update PLAN.md — Add a task under the current iteration with
- [ ]checkbox - Create a TodoWrite — Track the work item as in_progress
- Assess SRS impact — Check if a new requirement (REQ-XXX-NNN) is needed in the relevant
docs/SRS_*.md. If yes, add it with a test reference.
Only then proceed with implementation.
PLAN.md Format (STRICT)
- Markdown checklists with
- [ ]/- [x] - Version-numbered iterations: v0.1.0, v0.1.1, v0.2.0, etc.
- Each iteration has a title and summary
- Status table at the bottom
- Update in real-time as tasks are completed
powerplan MCP (PLAN.md operations)
PowerNote vendors powerplan as a git
submodule at powerplan/ and registers it in project .mcp.json.
- Server:
powerplan(stdio) —python powerplan/powerplan_server.py - Purpose: single-writer API over
PLAN.md(create iterations, complete tasks, current-iteration queries) without freeform thrash - Default plan: walk-up from cwd finds this repo’s root
PLAN.md - Setup after clone:
git submodule update --init --recursive # optional: pip install -e ./powerplan - Prefer MCP tools (
get_current_iteration,complete_task, …) over hand-editing PLAN checkboxes when the server is available. Restart the agent session after changing.mcp.jsonso tools load.
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 · 139 lines · 1,696 tokens per session scan A f8c64b63f129
PowerScroll CLAUDE.md is an instructions file published in the GitHub repository CynaCons/PowerScroll (0 stars, last pushed today), licensed MIT. It adds 1,696 tokens to every session, about $0.0085 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 2026-08-31.
Other instructions, from other repositories
anarlog AGENTS.md
AGENTS.md instructions for fastrepl/anarlog, covering commands, pre-commit verification, guidelines, code style and cli tui command architecture.
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).
markra AGENTS.md
AGENTS.md instructions for markrahq/markra, covering markra engineering guidelines, package management, tech stack, code organization and codemirror editor invariants.
mdread CLAUDE.md
Instructions for techjewel/mdread, covering claude.md, what this is, commands, architecture and styles (scss).
plano CLAUDE.md
Claude Code instructions for zqkra/plano, covering claude.md, what plano is, commands, environment gotchas (windows — hit these during setup) and environment gotchas (linux / fedora kde — port-specific).