Borrowing it
Nothing to install: this file belongs to IsoCodeCrafter/PCP. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/IsoCodeCrafter/PCP/main/.cursorrulesgit clone --depth 1 https://github.com/IsoCodeCrafter/PCPWrote 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/isocodecrafter/pcp/cursorrules)<a href="https://agentmods.dev/rules/isocodecrafter/pcp/cursorrules"><img src="https://agentmods.dev/badge/rules/isocodecrafter/pcp/cursorrules/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/isocodecrafter/pcp/cursorrules"><img src="https://agentmods.dev/badge/rules/isocodecrafter/pcp/cursorrules.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 | $0.00658 | $0.00658 |
| Opus 5 | $0.00329 | $0.00329 |
| Sonnet 5 | $0.00132 | $0.00132 |
| Haiku 4.5 | $0.00066 | $0.00066 |
Grade A, and why
cursorrules 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 — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.
📌 Project Context Protocol (PCP) Directives
Automatically synced by PCP CLI (v0.1.2). Do not edit between boundary markers.
This repository adheres to the Project Context Protocol (PCP) standard for preserving, organizing, and maintaining persistent project continuity across human and AI contributors.
🧭 Context Location & Architecture
- Canonical Entry Point:
context/manifest.yaml - Core Knowledge Components:
context/ARCHITECTURE.md: Structural boundaries, component domains, and non-negotiable architectural constraints.context/DECISION_LOG.md: Historical architectural decision records (ADRs) with rationale and consequences.context/KNOWLEDGE.md: Durable domain rules, business invariants, and technical conventions.context/OPEN_WORK.md: Active tasks, priority backlog items, and technical debt tracking.context/OPERATIONAL_GUIDE.md: Setup, testing, contribution, deployment, and operational runbooks.
🤖 AI Contributor Protocol
- Session Handshake (Cold-Start Briefing):
- At the beginning of any session or upon first interaction, inspect
context/manifest.yaml, the latest entry incontext/DECISION_LOG.md, and active tasks incontext/OPEN_WORK.md. - Provide a concise (3-4 lines max), token-friendly greeting card:
[PCP Active | <project-name>] ⚡ Last Decision: DEC-XXXX (<title> - by <author>) 📋 Active Task: WORK-XXXX (<title>) Ready. How should we proceed?
- At the beginning of any session or upon first interaction, inspect
- Context-First Discovery:
- Before suggesting architectural changes or writing code, consult the relevant context components.
- Preserve established knowledge: Never rediscover or contradict past decisions in
DECISION_LOG.mdwithout an explicit rationale.
- Autonomous Context Synchronization (Gravity Matching):
- Do NOT ask repetitive confirmation questions like "Should I record this decision?".
- When introducing structural/architectural changes (new dependencies, schema changes, state management patterns, API contracts) or completing open tasks:
- Compare against existing entries to match the appropriate abstraction level.
- Proactively bundle the context update (
DECISION_LOG.md,OPEN_WORK.md, orKNOWLEDGE.md) directly into the code change using valid RFC-0001 schema and sequential IDs. - Report the context update in your final response summary (e.g., "Context updated: DEC-0003 & WORK-0001 marked completed").
- The human authorizes the change naturally via Git diff / PR review.
- Context Integrity Verification:
- Ensure YAML frontmatters, IDs, and cross-references remain valid:
npx @craftsolutions/pcp check
- Ensure YAML frontmatters, IDs, and cross-references remain valid:
- Context Bundling:
- For external reasoning or web chat review, active context can be compiled via:
npx @craftsolutions/pcp pack -a
- For external reasoning or web chat review, active context can be compiled via:
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 · 47 lines · 658 tokens per session scan A a5cebb275f7c
cursorrules is a cursor rule published in the GitHub repository IsoCodeCrafter/PCP (0 stars, last pushed 3d ago), licensed MIT. It adds 658 tokens to every session, about $0.0033 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 2026-09-09.
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…
context-recorder-system
A modular system for recording project context, decisions, requirements, and lessons in structured files. It divides the recorder into core, template, advanced, and edge-case modules.
self-improving-obsidian-llm-wiki
LLM Wiki OS operating rules.