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/marv1nnnnn/mouse/plan_file_structure.mousegit clone --depth 1 https://github.com/marv1nnnnn/mouseWhat 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 | $0.00985 | $0.00985 |
| Opus 5 | $0.00492 | $0.00492 |
| Sonnet 5 | $0.00197 | $0.00197 |
| Haiku 4.5 | $0.00098 | $0.00098 |
Grade A, and why
plan_file_structure.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 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 — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mouse Execution Plan (For Task MOUSE#TASK_0001)
Protocol Version: Mouse Protocol V3.6
CRITICAL: Agent MUST use SEQUENTIAL NUMBERING for ALL identifiers and log entries.
All file paths are workspace-relative unless explicitly stated otherwise.
MANDATORY YAML Frontmatter for a Mouse PlanFile
TaskID: MOUSE#TASK_0001 # MUST match the parent TaskID. PlanTitle: "Execution Plan for User Survey Data Processing & Report Generation" GenerationOrder: 1 # Sequential number for this plan's generation. LastUpdatedOrder: 1 # Sequential, incremented on each significant modification by Agent.
SubTasks:
- SubTaskID: MOUSE#TASK_0001-SUB.01 # Sequential for this TaskID.
Objective: "Load, validate, and clean raw survey data (
data/raw/survey_results_q3_2023.csv)." Status: Pending # CRITICAL: Agent manages this. MUST be synchronized with FinalOutputSummary.completion_status upon termination. # Allowed values: Pending | InProgress | CompletedSuccessfully | CompletedWithWarnings | Failed | BlockedDeliverables: Optional. Specific, verifiable outputs for THIS sub-task.
- "Cleaned data file
ExecutionLog: # Detailed, append-only log of Agent actions for THIS sub-task. Each entry is a structured YAML object.data/intermediate/cleaned_survey_data.parquet."- Step: 1 # Example: Populated by Agent when starting this sub-task
ActionDescription: "Starting SubTask MOUSE#TASK_0001-SUB.01. SubTask.Status updated to InProgress."
Rationale: "Initiating first sub-task."
OutcomeObservation: "SubTask MOUSE#TASK_0001-SUB.01 Status is now InProgress."
... Further execution steps logged here by Agent ...
- Step: N # Example: Populated by Agent upon finishing/failing this sub-task
ActionDescription: "Finalized SubTask MOUSE#TASK_0001-SUB.01. Populated FinalOutputSummary. SubTask.Status field in PlanFile YAML updated to reflect FinalOutputSummary.completion_status ('CompletedSuccessfully')."
Rationale: "All steps completed successfully."
OutcomeObservation: "SubTask MOUSE#TASK_0001-SUB.01 Status is now CompletedSuccessfully."
FinalOutputSummary: null # REQUIRED. Populated by Agent upon sub-task termination (see Mouse Protocol 3.3.1). # Remains null until sub-task reaches a terminal state. # Example structure (Agent fills this in): # completion_status: "CompletedSuccessfully" # REQUIRED. Drives SubTask.Status. Values: "CompletedSuccessfully", "CompletedWithWarnings", "Failed", "BlockedByDependency", "BlockedAwaitingClarification" # summary_message: "Data loaded, validated, and cleaned. 1050 valid records." # REQUIRED. # output_artifacts: # Optional # - path: "data/intermediate/cleaned_survey_data.parquet" # type: "file" # description: "Cleaned survey data." # checksum_sha256: "abc123def456..." # key_observations_or_errors: "No errors. 5 records dropped." # REQUIRED, even if "None." # clarification_question_for_user: null # String if BlockedAwaitingClarification # error_details_if_failed: null # String if Failed
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 · 71 lines · 985 tokens per session scan A c5cb23d9586f
plan_file_structure.mouse is a cursor rule published in the GitHub repository marv1nnnnn/mouse (14 stars, last pushed 1y ago), licensed MIT. It adds 985 tokens to every session, about $0.0049 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
ankra-cli
Ankra CLI rules and best practices for managing Kubernetes clusters via the Ankra platform.
code-style-consistency-cursorrules-prompt-file
Cursor rules for code development with style consistency integration.
go-backend-scalability-cursorrules-prompt-file
Cursor rules for Go development with backend scalability.
cypress-api-testing-cursorrules-prompt-file
Cursor rules for Cypress development with API testing.
cloudflare-email-telegram-cursorrules-prompt-file
Cursor rules for setting up email-to-Telegram forwarding via Cloudflare Email Routing and Workers using the mail2tg CLI.
github-cursorrules-prompt-file-instructions
Cursor rules for GitHub development with instructions integration.