Borrowing it
Nothing to install: this file belongs to vscarpenter/gsd-task-manager. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/vscarpenter/gsd-task-manager/main/CLAUDE.mdgit clone --depth 1 https://github.com/vscarpenter/gsd-task-managerWrote 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/vscarpenter/gsd-task-manager/claude-md)<a href="https://agentmods.dev/instructions/vscarpenter/gsd-task-manager/claude-md"><img src="https://agentmods.dev/badge/instructions/vscarpenter/gsd-task-manager/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/vscarpenter/gsd-task-manager/claude-md"><img src="https://agentmods.dev/badge/instructions/vscarpenter/gsd-task-manager/claude-md.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.03044 | $0.03044 |
| Opus 5.5 | $0.01218 | $0.01218 |
| Sonnet 5.5 | $0.00609 | $0.00609 |
| Haiku 4.5 | $0.00304 | $0.00304 |
Grade A, and why
gsd-task-manager 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 6d 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 — 185 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
Guidance for Claude Code working in this repository. Coding standards live in @coding-standards.md (imported). Path-scoped rules live in .claude/rules/*.md and auto-load when their globs match.
Project Overview
GSD Task Manager is a privacy-first Eisenhower matrix task manager built with Next.js 16 App Router. All data is stored locally in IndexedDB via Dexie, with JSON export/import for backups. The app is a PWA that works completely offline.
Key Features:
- Single-Matrix UI (v9) — Simplified single-matrix layout with capture-bar; see
docs/adr/0011-v9-single-matrix-refactor.md - Optional Cloud Sync — Multi-device sync via self-hosted PocketBase at
https://api.vinny.io(OAuth with Google/GitHub) - MCP Server Integration — AI-powered task management through Claude Desktop with natural language queries
- Realtime Sync — PocketBase SSE (Server-Sent Events) for instant cross-device updates
- iOS-style Settings — Full-page settings with grouped layout and modular sections (
components/settings-page/) - Command Palette — Global ⌘K/Ctrl+K task search and actions are wired through
components/matrix-simplified/app-shell.tsx
Path-scoped rules (auto-loaded by glob — open these only when working in the matching subtree):
.claude/rules/pocketbase-sync.md— PocketBase v0.23+ gotchas, sync architecture, OAuth callback debugging.claude/rules/testing.md— Test runner, TDD workflow, jsdom/bun gotchas.claude/rules/sw-cache.md— Service worker multi-cache strategy (ADR 0012).claude/rules/mcp-server.md— MCP server package conventions and tool layout.claude/rules/archive-tombstone.md— ThearchivedTaskstombstone invariant (ADR 0013); read before writing totasksorarchivedTasks
Design Context
Strategic design intent lives in PRODUCT.md (root). Read it before UI/UX work or when running any /impeccable command.
- Register:
product— design serves the task (the matrix, capture bar, settings, dashboard), not a marketing surface. - Personality: calm & focused. Anti-references: flashy-AI startup, gamified todo toy, dense enterprise PM, generic SaaS dashboard.
- Principles: tool disappears into the task · privacy is the foundation · the matrix is the argument · earned familiarity over novelty · delight in moments, restraint on pages.
- Visual system: Inkwell 1.4.0 "GSD Editorial" — warm paper surfaces, graphite ink, Newsreader serif display over system sans, and restrained tide (#2C6680) for global interaction, with four matrix-only quadrant families. Runtime primitives live in
app/css/inkwell-tokens.css; quadrant washes/headers live inapp/globals.css; the durable contract isDESIGN.mdplus.ui-craft/brief.mdand.ui-craft/tokens.md. Tide is interaction ink, never gradient decoration. WCAG AA is the baseline, and quadrant titles must use--q*-inkrather than raw pigment.
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.
- 6d ago Changed · +19 tokens per session 168bb1aa015b
- 11d ago Changed · +53 tokens per session 2d57f06c8d51
- 22d ago Changed 081c23475a88
- 1mo ago Changed · +2 lines · +114 tokens per session 64454191b559
- 2mo ago First seen · 183 lines · 2,858 tokens per session scan A c94971b9da59
gsd-task-manager CLAUDE.md is an instructions file published in the GitHub repository vscarpenter/gsd-task-manager (40 stars, last pushed yesterday), licensed MIT. It adds 3,044 tokens to every session, about $0.0122 per session on Opus 5.5. 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
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.