self_improve

A set of rules for improving Cursor rules as code patterns and recommended practices change.

In plain words
What is it for?
Use it when reviewing Cursor rules and adapting them to new patterns or practices.
Why use it?
It encourages the rule set to be updated instead of leaving outdated guidance in place.

Cursor rule for Cursor

Install

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.

agentmods
npx agentmods add rules/eyaltoledano/claude-task-master/self_improve
Clone the repo
git clone --depth 1 https://github.com/eyaltoledano/claude-task-master

Made for: Cursor.

Per session 530 This file is loaded in full into every session.
When invoked 530 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin unknown No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00530 $0.00530
Opus 5 $0.00265 $0.00265
Sonnet 5 $0.00106 $0.00106
Haiku 4.5 $0.00053 $0.00053

Measured 3d ago against content hash b1ad380d15cc, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

self_improve 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.

.cursor/rules/self_improve.mdc · 73 lines

The source is not reproduced here

No licence file

A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.

Read it on GitHub

Changes

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.

  1. 3d ago First seen · 73 lines · 530 tokens per session scan A b1ad380d15cc

Subscribe to this mod's changes

self_improve is a cursor rule published in the GitHub repository eyaltoledano/claude-task-master (28,040 stars, last pushed 4mo ago), with no licence file. It adds 530 tokens to every session, about $0.0027 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.

Related

Other cursor rules, from other repositories

composer-2.5-execution

Guard execution of approved plan/burndown work: forbid reward hacking and feature deletion; require checkpoints, context discipline, safe terminal use, and fresh verification. Apply to approved plan-.md, complete-everything, or burndown-full runs; binding for any implementation model.

kensaurus/cursor-kenji · 1,062 tokens

cursor-jr-routing

Маршрутизация к CursorJr для русскоязычных новичков: первый запуск Cursor, вопросы про Agent/Ask/Plan/Debug, rules, skills, MCP, автоматизацию, просьбы объяснить «на пальцах». Делегируй Task(cursor-jr), не дублируй длинные объяснения в основном чате.

Horosheff/cursor-jr · 73 tokens

composer-orchestration

Subagents, plan mode, parallel workstreams, long-running tasks — when to delegate vs do inline.

madebyaris/cursor-composer-rules · 20 tokens

graphstack

GraphStack v4.7.1 — Orchestrated, graph-first, GNAP-tracked AI development (cross-platform).

MertCapkin/GraphStack · 1,573 tokens

workspace-rules

工作区规范 — 安全、操作边界、工具调用风格、记忆写入哲学.

nongjun/feishu-cursor-claw · 657 tokens

create-rule-agent

This rule is responsible for creating and updating Cursor rules. Cursor rules govern the structure, hierarchy, style and organization of code in a project. This rule should be invoked in Agent mode when: 1. a user wants to create a new cursor rule, 2. a user wants to update or change an existing rule, 3. user wants…

usrrname/cursorrules · 3,429 tokens