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/copperdogma/cursor-project-bootstrapperWrote 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/copperdogma/cursor-project-bootstrapper/scratchpad)<a href="https://agentmods.dev/rules/copperdogma/cursor-project-bootstrapper/scratchpad"><img src="https://agentmods.dev/badge/rules/copperdogma/cursor-project-bootstrapper/scratchpad/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/copperdogma/cursor-project-bootstrapper/scratchpad"><img src="https://agentmods.dev/badge/rules/copperdogma/cursor-project-bootstrapper/scratchpad.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 | $0.00485 | $0.00485 |
| Opus 5.5 | $0.00194 | $0.00194 |
| Sonnet 5.5 | $0.00097 | $0.00097 |
| Haiku 4.5 | $0.00049 | $0.00049 |
Grade A, and why
scratchpad 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 2mo 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
Work Phase Scratchpad Memory File
scratchpad.md exists as your session context for the current work. It's a lightweight, focused view of what you're doing right now.
Important: Detailed implementation history belongs in individual story files (see build-story.md command). The scratchpad is for active session context only, not a complete history repository.
Suggested structure for scratchpad.md:
- Current Story: Link to the story you're currently working on from
/docs/stories.md - Current Task: Brief description of what you're working on this moment
- Plan Checklist: Quick checklist of work required for the current task/story
- Issues/Blockers: Active issues or blockers right now
- Decisions Made: Recent decisions that affect current work (detailed decisions go in story work logs)
If scratchpad.md is missing any of these sections, restore them immediately. Never remove this structure.
Instructions
- Always add tasks as checklists so they can be tracked.
- Follow
project-management.mdcfor work-specific instructions. - Use scratchpad.md for current session context - what you're doing right now.
- Detailed implementation history (attempts, failures, solutions) should go in story work logs (see
build-story.mdcommand). - Frequently suggest to the user what the next obvious steps are and suggest the most logical one.
- Reorganize scratchpad.md now and then, putting unfinished tasks at the top and finished ones at the bottom.
- Update
/docs/stories.mdwith story statuses and progress. - Archive scratchpad only on phase transitions or major milestones (not after every task). Detailed history is preserved in story work logs.
- When starting a new story, reset or update scratchpad.md to focus on the new work. Previous story details are in that story's work log.
Keep it concise (<300 lines): summarize or remove outdated info regularly to prevent overloading the context. Focus on the current session and immediate next 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.
- 2mo ago First seen · 34 lines · 485 tokens per session scan A cc07fc703ac5
scratchpad is a cursor rule published in the GitHub repository copperdogma/cursor-project-bootstrapper (4 stars, last pushed 11mo ago), licensed MIT. It adds 485 tokens to every session, about $0.0019 per session on Opus 5.5. 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
mempalace-recall-always
Always-on MemPalace recall — search the palace before answering about past work, people, projects, or prior decisions.
dreamd-recall
Search dreamd at the start of a task and quote a hit. Append when the user corrects you or states a decision.
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.