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.
git clone --depth 1 https://github.com/zackiles/cursor-configWrote 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/zackiles/cursor-config/remove-plans)<a href="https://agentmods.dev/rules/zackiles/cursor-config/remove-plans"><img src="https://agentmods.dev/badge/rules/zackiles/cursor-config/remove-plans/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/zackiles/cursor-config/remove-plans"><img src="https://agentmods.dev/badge/rules/zackiles/cursor-config/remove-plans.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 | $0.00000 | $0.00814 |
| Opus 5.5 | $0.00000 | $0.00326 |
| Sonnet 5.5 | $0.00000 | $0.00163 |
| Haiku 4.5 | $0.00000 | $0.00081 |
Grade A, and why
remove-plans 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.
What it actually says
Clean and Remove Old Plans NOW
Before proceeding with this conversation or the current message from the user you will clean up your specialized on-disk files that were used for planning. To cleanup your files take the following steps one by one using your tools:
-
Initialize two variables in your memory now named
filesToReview[string]andfilesToDelete[string]then move to step 2. -
Get a list of all files matching the pattern
./cursor/memory/todo*.mdusing thelist_dirtool:# EXAMPLE COMMAND: Adapt the path as needed for your workspace structure list_dir(relative_workspace_path: ".cursor/memory", explanation: "Listing todo files in memory directory")Add the absolute paths of matching files as strings to the array in the variable
filesToReview[string]. Examples of files that would match this pattern:./cursor/memory/todo7-checklist.md,./cursor/memory/todo-random-characters901..md,./cursor/memory/todo7-june-23-2005.md. -
Pop off and remove an absolute path from the
filesToReview[string]and use it in step 4. If the array is empty then skip all steps and move directly to step 10 (the final step). -
Get the full contents of the file at absolute path received from step 3 using the
read_filetool:# EXAMPLE COMMAND: Replace {file_path} with the actual path from filesToReview read_file(target_file: "{file_path}", should_read_entire_file: true)Then move to step 5 where you will use it.
-
Review each and every single checklist or action item found in the file contents from step 4 that have NOT been finished or marked complete. If you find uncompleted items remove the file contents and path from your memory and move back to step 2. If ALL action items HAVE been completed, then move to step 6.
-
ALL ITEMS IN FILE HAVE BEEN COMPLETED: if this file has already been worked on and all items completed, then we will mark it for deleting by adding its absolute path to
filesToDelete[string]and move back to step 2. -
If there are no more file paths in
filesToReview[string]or it's empty, then check thefilesToDelete[string]array: if it contains any paths, move to step 8; if it is empty, then move to step 9. -
Take the absolute paths from step 7, let the user know the list of old files you've found in your memory, and then batch delete all of them from the users system using a single terminal command:
# EXAMPLE COMMAND: Replace with actual file paths from filesToDelete array run_terminal_cmd(command: "rm {file1_path} {file2_path} {file3_path}", is_background: false, explanation: "Deleting completed plan files")Where {file1_path}, {file2_path}, etc. are the actual file paths from the
filesToDelete[string]array. Once the files are deleted, move to step 9. -
Empty the
filesToReview[string]array and then move to step 10. -
FINAL STEP: Confirm both the
filesToDelete[string]andfilesToReview[string]arrays are empty or no longer exist. If they're both empty, your work is complete, and you can now handle the users message or end the conversations turn if there are no other user requests or messages to act on.
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 First seen · 46 lines · 0 tokens per session scan A 23e11998b2a9
remove-plans is a cursor rule published in the GitHub repository zackiles/cursor-config (17 stars, last pushed 1y ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 814 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
mempalace-recall-always
Always-on MemPalace recall — search the palace before answering about past work, people, projects, or prior decisions.
dreamd-recall
Recall lessons, decisions, and prior context from the .agent/ memory daemon. Use when starting work in a project that has a .agent/ folder, when the user references a past decision, or when you are about to make a choice that has a documented prior.
session-memory
Use at conversation wrap-up or when the user explicitly indicates end-of-session — capture residual lessons not captured in-flight.
common_memory_bank
I am Cursor, an expert software engineer with a unique characteristic: my memory resets completely between sessions. This isn't a limitation - it's what drives me to maintain perfect documentation. After each reset, I rely ENTIRELY on my Memory Bank to understand the project and continue work effectively. I MUST read…
self-improving-obsidian-llm-wiki
LLM Wiki OS operating rules.
memsprout
Cursor rule "memsprout" from memsprout/agents, covering using memsprout, search first, capturing, spaces and topics and files.