What is task_structure_example.mouse?

A template and set of rules for describing Mouse tasks in YAML frontmatter. YAML is a human-readable format for structured settings and metadata.

Use it to define data-processing or similar tasks with required files, procedures, expected results, limits, and tools.

It makes task records consistent, uniquely numbered, and clear about inputs, steps, outputs, and success conditions.

task_structure_example.mouse — Cursor rule by marv1nnnnn

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/marv1nnnnn/mouse/task_structure_example.mouse

Clone the repo

git clone --depth 1 https://github.com/marv1nnnnn/mouse

Made for: Cursor.

Per session 731 This file is loaded in full into every session.

When invoked 731 The same file — it is already loaded in full.

Security scan A 0 findings. Scan, not verified.

Origin original 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.

Model	Per session	Once invoked
Fable 5	$0.00731	$0.00731
Opus 5	$0.00365	$0.00365
Sonnet 5	$0.00146	$0.00146
Haiku 4.5	$0.00073	$0.00073

Measured yesterday against content hash aa4a07b33a64, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

task_structure_example.mouse 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 yesterday.

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/templates/task_structure_example.mouse.mdc · 69 lines

How it starts

The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MANDATORY YAML Frontmatter for a Mouse Task

Protocol Version: Mouse Protocol V3.6

All identifiers and sequential fields MUST use sequential numbering.

TaskID: MOUSE#TASK_0001 # Example. MUST be unique & sequential. Title: "Example Task: Process User Survey Data and Generate Insights Report" Description: | This task involves processing raw user survey data, performing analysis, and generating a comprehensive insights report.

Background/Context: Quarterly user feedback initiative.
Specific Inputs:
- File: data/raw/survey_results_q3_2023.csv
- Schema: docs/schemas/survey_input_schema.json
- Config: config/processing_rules.yaml
Detailed Requirements/Steps: (Summarized - full detail in protocol or body)
1. Load, validate, clean data.
2. Perform sentiment analysis.
3. Aggregate responses.
4. Generate insights and visualizations.
5. Compile markdown report.
Desired Outputs & Verifiable Success Criteria:
- Output reports/user_insights_q3_2023.md with specified content.
- Output data/processed/survey_processed_q3_2023.parquet.
Constraints & Non-Functional Requirements:
- Complete within 1 hour.
- Use 'vaderSentiment' library. SubmittedBy: User SubmissionOrder: 1 # Sequential. Priority: High # Critical | High | Medium | Low. Status: Pending # Initial. See Mouse Protocol V3.6 Section 2.4 for lifecycle. AssignedTo: Agent

Dependencies: Optional array of TaskIDs.

- MOUSE#TASK_0000

Deliverables: # Must align with 'Desired Outputs & Verifiable Success Criteria'.

"Markdown report reports/user_insights_q3_2023.md with all specified sections."
"Parquet file data/processed/survey_processed_q3_2023.parquet." EstimatedEffort: M # S | M | L | X. PlanFile: ../plans/MOUSE#TASK_0001_plan.md # Relative path. Mandatory for L/X, recommended for complex M.

Tags: Optional array of keywords.

- "data-analysis"

- "python"

ExecutionOrder: null # Null initially. Set by Agent to sequential number when processing begins. CompletionOrder: null # Null initially. Set by Agent to sequential number at terminal state. HistoryLog: # CRITICAL: Array of structured YAML log objects. Agent MUST log ALL specified events.

Step: 1 Actor: User EventType: CREATED FromStatus: null ToStatus: Pending Details: "Task defined: Process Q3 survey data."

- Step: 2

Actor: Agent # Or User

EventType: STATE_TRANSITION # Or TASK_TRIAGED

FromStatus: Pending

ToStatus: Ready

Details: "Task MOUSE#TASK_0001 moved to Ready queue."

Read the full file on GitHub · 69 lines

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.

yesterday First seen · 69 lines · 731 tokens per session scan A aa4a07b33a64

Subscribe to this mod's changes

task_structure_example.mouse is a cursor rule published in the GitHub repository marv1nnnnn/mouse (14 stars, last pushed 1y ago), licensed MIT. It adds 731 tokens to every session, about $0.0037 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.

Planning ai cursor cursorrules task-management vibe-coding

task_structure_example.mouse