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/bluewings1211/codebase-rag/process-task-listgit clone --depth 1 https://github.com/bluewings1211/codebase-RAGWhat 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 | $0.00000 | $0.00388 |
| Opus 5 | $0.00000 | $0.00194 |
| Sonnet 5 | $0.00000 | $0.00078 |
| Haiku 4.5 | $0.00000 | $0.00039 |
Grade A, and why
process-task-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 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.
Copies of this mod
3 near-identical copies found in the catalogue:
- process-task-list — 88% identical, 13 lines differ
- 1002-task-list — 88% identical, 23 lines differ
- process-task-list — 83% identical, 21 lines differ
What it actually says
Task List Management
Guidelines for managing task lists in markdown files to track progress on completing a PRD
Task Implementation
- One sub-task at a time: Do NOT start the next sub‑task until you ask the user for permission and they say “yes” or "y"
- if user reply yolo, you Can start next sub-task without permission
- Completion protocol:
- When you finish a sub‑task, immediately mark it as completed by changing
[ ]to[x]. - If all subtasks underneath a parent task are now
[x], also mark the parent task as completed.
- When you finish a sub‑task, immediately mark it as completed by changing
- Stop after each sub‑task and wait for the user’s go‑ahead.
Task List Maintenance
-
Update the task list as you work:
- Mark tasks and subtasks as completed (
[x]) per the protocol above. - Add new tasks as they emerge.
- Mark tasks and subtasks as completed (
-
Maintain the “Relevant Files” section:
- List every file created or modified.
- Give each file a one‑line description of its purpose.
AI Instructions
When working with task lists, the AI must:
- Regularly update the task list file after finishing any significant work.
- Follow the completion protocol:
- Mark each finished sub‑task
[x]. - Mark the parent task
[x]once all its subtasks are[x].
- Mark each finished sub‑task
- Add newly discovered tasks.
- Keep “Relevant Files” accurate and up to date.
- Before starting work, check which sub‑task is next.
- After implementing a sub‑task, update the file , use git as version control and then pause for user approval.
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 · 40 lines · 0 tokens per session scan A a02d13e870ad
process-task-list is a cursor rule published in the GitHub repository bluewings1211/codebase-RAG (15 stars, last pushed 8mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 388 tokens. 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
cursorrules
You are an expert in developing information retrieval, re-ranking, and retrieval-augmented generation (RAG) systems using Python, with a focus on PyTorch and state-of-the-art NLP models.
trigger.advanced-tasks
Comprehensive rules to help you write advanced Trigger.dev tasks.
vios-sqa
VIOS SQA agent. One-click build → deploy → test → UI validation cycle. Use when asked to run regression tests, check test results, deploy for testing, or verify UI behavior.
cursorrules
This file contains project-specific instructions for AI assistants working on the CICADA codebase.
cursorrules
When building AI apps with this project, follow these conventions.
mcp-server
MCP (Model Context Protocol) server architecture and implementation.