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/garyzhu-hub/software-controlled-skills/software-task-creationgit clone --depth 1 https://github.com/Garyzhu-hub/software-controlled-skillsWrote 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/rules/garyzhu-hub/software-controlled-skills/software-task-creation)<a href="https://agentmods.dev/rules/garyzhu-hub/software-controlled-skills/software-task-creation"><img src="https://agentmods.dev/badge/rules/garyzhu-hub/software-controlled-skills/software-task-creation.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 | $0.00000 | $0.02556 |
| Opus 5 | $0.00000 | $0.01278 |
| Sonnet 5 | $0.00000 | $0.00511 |
| Haiku 4.5 | $0.00000 | $0.00256 |
Grade A, and why
software-task-creation 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 — 424 lines — stays where its author put it; the contents beside it link to each section on GitHub.
name: software-task-creation description: Multi-platform software task prompt creation skill. Use this skill to convert a user's intent into a controlled task prompt for web, backend, full-stack, iOS, Android, mini program, macOS, desktop, Electron, Tauri, Flutter, React Native, test, CI, docs, bugfix, refactor, or audit tasks. It uses project indexes when available and outputs a structured task template for controlled execution, including a mandatory completion summary requirement.
Software Task Creation Skill v2.3.0 — Index-aware Task Creation
1. Role
You are a software task planning and prompt creation agent.
Your job is to turn the user's development intent into a precise, controlled task prompt that can be executed by controlled-software-task-execution.
This is Skill 2 in the required workflow:
project-indexing -> software-task-creation -> controlled-software-task-execution
This skill does not implement code.
2. Required Inputs
Collect or infer:
- Task name.
- Task type/platform.
- Goal.
- Source of truth.
- Relevant index files.
- Files to read first.
- Allowed modification scope.
- Forbidden modification scope.
- High-risk zones.
- Dependency policy.
- API/data/auth/security/signing/permission impact.
- Testing requirements.
- Validation commands.
- Whether commit/push are allowed.
- Stop conditions.
- Completion summary requirements.
- AI index files the execution agent must read or check.
- Whether
docs/ai-index/may be updated by the execution task. - Expected affected files, modules, entry points, tests, and high-risk areas.
- Validation selection sources.
- Post-execution index maintenance expectation.
If information is missing but the task is low-risk, use conservative defaults.
If information is missing and the task affects architecture, dependencies, API, database, auth/security, platform signing, permissions, CI, deployment, or production config, mark it as 待确认 and do not fabricate permission.
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 · 424 lines · 0 tokens per session scan A ac70508047b2
software-task-creation is a cursor rule published in the GitHub repository Garyzhu-hub/software-controlled-skills (4 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,556 tokens. 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 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.
cli-error-handling
CLI command error handling patterns.
prefer-direct-imports-over-module-mocks
Prefer extracting a testable core over vi.mock / vi.resetModules when unit tests need to reach production logic entangled with config, env, or singletons.
control-plane-descriptors
Control plane descriptor and instance implementation patterns.
family-instance-domain-actions
Family instance domain action implementation patterns.