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/compozy/gograph/task-generate-listgit clone --depth 1 https://github.com/compozy/gographWhat 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 | $0.00020 | $0.02227 |
| Opus 5 | $0.00010 | $0.01113 |
| Sonnet 5 | $0.00004 | $0.00445 |
| Haiku 4.5 | $0.00002 | $0.00223 |
Grade A, and why
task-generate-list 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 2d 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 — 211 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Rule: Generating a Task List from a PRD
<source_of_truth_policy> SINGLE SOURCE OF TRUTH: Taskmaster JSON
tasks.json(generated by taskmaster) is the authoritative task store_tasks.mdand individual<num>_task.mdfiles are generated views from the JSON- All task status updates, modifications, and tracking must be done through taskmaster MCP tools
- Markdown files are for human readability and should be regenerated when JSON changes
- Never manually edit Markdown task files - use taskmaster commands for all task operations </source_of_truth_policy>
<output_specification>
- Format: Markdown (
.md) - Locations:
- Feature folder:
/tasks/prd-[feature-slug]/ - Tasks summary file:
/tasks/prd-[feature-slug]/_tasks.md(generated from JSON) - Individual task files:
/tasks/prd-[feature-slug]/<num>_task.md(generated from JSON) - Authoritative source:
/tasks/prd-[feature-slug]/tasks.json(taskmaster managed) - Complexity report:
/tasks/prd-[feature-slug]/task-complexity-report.json - Merged file:
/tasks/prd-[feature-slug]/merged_prd_techspec.md</output_specification>
- Feature folder:
Process
<process_steps>
- Receive PRD Reference: The user points the AI to a specific PRD file
- Verify Tech Spec: Confirm that a corresponding tech spec document exists (
tasks/prd-[feature-slug]/_techspec.md). If not, remind the user to create it using prd-tech-spec.mdc before proceeding with task generation. - Generate Merged File: Run
mf ./tasks/prd-[feature-slug]to generate a merged file containing the PRD + techspec (merged_prd_techspec.md) - Create Taskmaster Tag: Using the taskmaster MCP, create a tag for this feature implementation
- Generate Taskmaster Tasks: Use taskmaster's parse-prd functionality with the merged file to generate the initial task structure (
tasks.json) - Generate Complexity Report: Use taskmaster to analyze task complexity and generate the complexity report (
task-complexity-report.json) - Generate Tasks Summary: Based on the taskmaster output and complexity analysis, create the
_tasks.mdfile following the established format - Parallel Agent Analysis: ⚠️MUST: For each task under the prd-[slug], spin up parallel agents to provide a final analysis. Check based on the current architecture and files if we are duplicating stuff or forgetting something - a general analysis using our current architecture as review before starting the tasks
- Wait for Confirmation: Present the analysis results to the user and inform them: "I have completed the task generation and architectural analysis. Ready to proceed with implementation? Respond with 'Go' to start."
- Generate Individual Task Files: Create separate files for each parent task in
/tasks/prd-[feature-slug]/<num>_task.md</process_steps>
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.
- 2d ago First seen · 211 lines · 20 tokens per session scan A e43b083c3d84
task-generate-list is a cursor rule published in the GitHub repository compozy/gograph (9 stars, last pushed 1y ago), licensed MIT. It adds 20 tokens to every session and 2,227 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 2026-08-31.
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.
typescript
Changes to these high-fan-out internals can affect every message, delta, element, or rerun. Keep work in them minimal, and benchmark changes with representative stress-test apps.
coolify-ai-docs
Master reference to all Coolify AI documentation in .ai/ directory.
python_lib
Tips and guidelines specific to the development of the Streamlit Python library, not applicable to scripts and e2e tests.
specs
This directory contains product and tech specs for Streamlit features.