Borrowing it
Nothing to install: this file belongs to shekarsiri/moo-tasks. 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/shekarsiri/moo-tasks/main/.windsurfrulesgit clone --depth 1 https://github.com/shekarsiri/moo-tasksWrote 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/shekarsiri/moo-tasks/windsurfrules)<a href="https://agentmods.dev/rules/shekarsiri/moo-tasks/windsurfrules"><img src="https://agentmods.dev/badge/rules/shekarsiri/moo-tasks/windsurfrules/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/shekarsiri/moo-tasks/windsurfrules"><img src="https://agentmods.dev/badge/rules/shekarsiri/moo-tasks/windsurfrules.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 | $0.00625 | $0.00625 |
| Opus 5.5 | $0.00250 | $0.00250 |
| Sonnet 5.5 | $0.00125 | $0.00125 |
| Haiku 4.5 | $0.00063 | $0.00063 |
Grade A, and why
windsurfrules 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 1mo 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.
This is a copy
100% identical to moo-tasks — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 31 lines — stays where its author put it; the contents beside it link to each section on GitHub.
🐮 Moo Tasks protocol
You are connected to the Moo Tasks MCP server. Every code change you make is tracked as a Moo task.
Before editing code
- Reading, searching and read-only commands (git status, running tests, builds) never need a task.
- Before your first edit, hold a claimed task:
- New work:
moo_quick_start(title, acceptanceCriteria, description, declaredFiles)creates and claims it in one call.goalIdis optional; without it the task goes under this workspace's "Ad-hoc work" goal. - Planned work:
moo_get_next_task(claim: true).
- New work:
- A small change is already finished?
moo_log_work(title, evidence)records it in one call.
Larger requests (multi-step or multi-file)
moo_create_goal(title, verbatimPrompt, description): the user's exact words plus a Markdown PRD.moo_create_task(goalId, tasks: [...]): atomic tasks, each with a description (overview and numbered plan),- [ ]acceptance criteria,declaredFilesanddependsOnTaskIds. Titles are plain text; usepriority,typeandtagsinstead of prefixes like "C1:".- Work through them with
moo_get_next_task(claim: true).
While working
moo_checkpoint(taskId, note)at milestones and before you stop: what is done, what is next, open questions. The next session resumes from these notes.- Found other work:
moo_capture_discovered_work(currentTaskId, title); addalreadyFixed: truefor a fix you made along the way. Need the user:moo_ask_human. An attempt failed:moo_log_attempt_failure. - Chose a library, pattern or trade-off:
moo_record_decision(title, context, choice, rationale).
Finishing
moo_complete_task(taskId, evidence: { testProof or outputSnippet, commandsRun }, criteria: [{ met, note }]): one answer per- [ ]acceptance item, in order. An unmet item is allowed with a note saying why; it is recorded as a deviation, so never mark it met.- If the workspace has a verify command, Moo runs it before accepting. Fix failures; pass
verifyOverrideonly when a failure is unrelated to your task. - Files changed since the claim are captured from git automatically. Parallel sub-agents each pass their own
agentId. - After a goal's last task, confirm with the user and close it:
moo_update_goal(goalId, status: 'completed', summary).
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.
- 1mo ago Changed · +2 lines · +159 tokens per session 6c55b4ffa497
- 1mo ago First seen · 29 lines · 466 tokens per session scan A 3897637f90ae
windsurfrules is a cursor rule published in the GitHub repository shekarsiri/moo-tasks (3 stars, last pushed 24d ago), licensed MIT. It adds 625 tokens to every session, about $0.0025 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 100% identical to moo-tasks, differing in 0 lines, and is treated as a copy.
Other cursor rules, from other repositories
task-list
Guidelines for creating and managing task lists in markdown files to track project progress.
project-epic-template-cursorrules-prompt-file
Cursor rules for project development with epic template integration.
monorepo-and-tooling
Rules for projects that may use a monorepo, a single repository containing multiple applications or shared packages. They also define Taskfile commands and how to keep environment settings outside the code.
state-transition-rule
A rule describing a request status flow from pending to approved and then to item creation. It is written in Chinese.
client-workflow-bootstrap
Cursor rule "client-workflow-bootstrap" from ulises-jeremias/agent-toolkit, covering agent vs skill rule — why agent (cite clause), when to use vs holistic, caller / skills / handoff, interview process and gate before generating.
swamr-state-manager
Swamr State Manager — tracks task progress, manages the execution pipeline, handles retries and escalation. Maintains swamr/state.json as the single source of truth for swarm progress.