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 rules/smekai/taskplanner/cursorrulesgit clone --depth 1 https://github.com/smekai/taskplannerWhat 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 | $0.02201 | $0.02201 |
| Opus 5 | $0.01100 | $0.01100 |
| Sonnet 5 | $0.00440 | $0.00440 |
| Haiku 4.5 | $0.00220 | $0.00220 |
Grade A, and why
cursorrules 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 2d 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 — 196 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Style
ESLint and Prettier cover the mechanical part — run npm run lint and npm run format before a PR.
This is enforced. npm run lint runs scripts/check-comments.js, which fails on any comment
in src/ outside src/test/. Machine directives (eslint-disable, @ts-expect-error,
prettier-ignore) are exempt. For the genuinely non-obvious case, prefix the comment with WHY:
and give the reason — the check counts those and lets them through.
Beyond that: a comment is a signal that the code is not clear enough yet. Before writing one, try to make it unnecessary — name the function after the comment, extract the condition into a named predicate, split the branch out. Names and types stay true as the code changes; comments drift.
Do not write:
- Comments that restate the code (
// increment nextId). - Doc blocks on every exported symbol. A precise name and type already say it.
- Section banners, decorative dividers, or step-by-step narration of a function body.
- Rationale that belongs in the commit message,
CHANGELOG.md, or a task's### Plan.
Do write, sparingly:
- A one-line note where the code must stay non-obvious: a workaround for an external bug, a deliberate deviation from an API contract, or an output format that must match byte-for-byte.
Comments belong in tests. A test name plus a short note explains the failure a case guards against far better than a comment sitting beside the code it guards.
If you find yourself explaining a function in prose, that is the signal to rewrite the function.
TaskPlanner — AI Agent Instructions
This project uses TaskPlanner for task management.
Tasks are stored as markdown files in the .tasks/ directory.
Task File Structure
Each state has its own file:
- Backlog →
BACKLOG.md - Next →
NEXT.md - In Progress →
IN_PROGRESS.md - Done →
DONE.md - Rejected →
REJECTED.md
Auxiliary file (optional rolling log, not a task state):
- Work Log →
WORK_LOG.md
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.
- 2d ago First seen · 196 lines · 2,201 tokens per session scan A feb2ac28f83a
cursorrules is a cursor rule published in the GitHub repository smekai/taskplanner (19 stars, last pushed 4d ago), licensed MIT. It adds 2,201 tokens to every session, about $0.0110 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 cursor rules, from other repositories
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
typescript
Changes to these high-fan-out internals can affect every message, delta, element, or rerun. Keep work in them minimal, and benchmark changes with representative stress-test apps.
coolify-ai-docs
Master reference to all Coolify AI documentation in .ai/ directory.
python_lib
Tips and guidelines specific to the development of the Streamlit Python library, not applicable to scripts and e2e tests.
specs
This directory contains product and tech specs for Streamlit features.