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.
git clone --depth 1 https://github.com/yodakeisuke/mcp-micromanage-your-agentWrote 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/yodakeisuke/mcp-micromanage-your-agent/task-plannning)<a href="https://agentmods.dev/rules/yodakeisuke/mcp-micromanage-your-agent/task-plannning"><img src="https://agentmods.dev/badge/rules/yodakeisuke/mcp-micromanage-your-agent/task-plannning/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/rules/yodakeisuke/mcp-micromanage-your-agent/task-plannning"><img src="https://agentmods.dev/badge/rules/yodakeisuke/mcp-micromanage-your-agent/task-plannning.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 | $0.00011 | $0.00289 |
| Opus 5 | $0.00005 | $0.00144 |
| Sonnet 5 | $0.00002 | $0.00058 |
| Haiku 4.5 | $0.00001 | $0.00029 |
Grade A, and why
task-plannning 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 8d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- task-plannning — 100% identical, 0 lines differ
What it actually says
Task Planning Guide
Purpose
- To design a structured implementation approach before any coding begins
- To ensure clear understanding of requirements and dependencies
- To divide tickets into small PRs and commits for easier review and integration
Output
- A comprehensive work plan organized by PRs and commits
- Each PR should be small, functional, and independently reviewable
- Each commit should represent an atomic change within its PR
- To minimize dependencies between PRs, ideally making them independently implementable
Method
Analysis Phase
- Analyze the task's architecture requirements thoroughly
- Explore and read all potentially relevant existing code and similar reference code
- Develop a meta architecture plan for the solution
Planning Approach
- Break down the task into smallest possible PRs
- Order PRs logically (e.g., setup → core logic → tests)
- Define 2-4 minimal atomic commits for each PR
- Prefer splitting tasks into PRs rather than large commits
Implementation Criteria
- Only proceed after achieving 100% clarity and confidence
- Ensure all affected parts of the codebase have been fully identified through dependency tracing
- The work plan must be approved by the user before implementation
Prohibited Actions
- Any implementation or code writing, even "example code"
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.
- 8d ago First seen · 37 lines · 11 tokens per session scan A d1a55d159257
task-plannning is a cursor rule published in the GitHub repository yodakeisuke/mcp-micromanage-your-agent (13 stars, last pushed 1y ago), licensed MIT. It adds 11 tokens to every session and 289 once invoked, about $0.0001 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
bootstrap-alwayson
Minimal always-required LLM fixes.
speclock
SpecLock project constraints — enforced automatically.
infura-mcp-server
Cursor rule "infura-mcp-server" from Qbandev/infura-mcp-server, covering infura mcp server project context, 📚 ai assistant resources, project overview, key statistics and technical architecture.
mcp-tools-readme
Keep README in sync when MCP tools change.
md-feedback-workflow
This project uses md-feedback for structured human review of implementation plans.
validate-design-early
Ask for design approval before implementing 100+ lines.