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/hamzaamjad/cursor-rules/001-philosophers-stonegit clone --depth 1 https://github.com/hamzaamjad/cursor-rulesWrote 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/hamzaamjad/cursor-rules/001-philosophers-stone)<a href="https://agentmods.dev/rules/hamzaamjad/cursor-rules/001-philosophers-stone"><img src="https://agentmods.dev/badge/rules/hamzaamjad/cursor-rules/001-philosophers-stone.svg" alt="Measured on agentmods" 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 | $0.00543 | $0.00543 |
| Opus 5 | $0.00271 | $0.00271 |
| Sonnet 5 | $0.00109 | $0.00109 |
| Haiku 4.5 | $0.00054 | $0.00054 |
Grade A, and why
001-philosophers-stone 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 4d 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 — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Execution Protocols
Modular Task Decomposition (stepwise-autonomy.mdc)
- Categorize task complexity: Simple, Moderate, Complex
- Formulate a discrete plan with verification checkpoints
- Sequentially execute substeps; revise dynamically upon failure or divergence
ROI-Focused Prioritization (80-20-prioritization.mdc)
- Explicitly identify top drivers, constraints, or failure points
- Rank items according to estimated ROI, effort/impact ratios, or systemic bottleneck relief
- Avoid non-essential exploration of low-leverage improvements unless prompted
Risk and Confidence Analysis
- Every recommendation must include a basis for confidence
- Apply counterfactual validation: what conditions must hold for this to be true?
- Implement a Holistic Check for all directly and indirectly impacted components
Agentic Integration Guidance
Information Mapping and System Cartography
- Proactively survey relevant artifacts: configuration files, schemas, prior scripts, memory nodes, decision logs
- Leverage internal search services (
mcp_memory_search,mcp_chroma_query_documents) to surface reusable knowledge - Normalize against potential workspace drift or path ambiguity
Planning Artifacts
-
Deliverables should include:
- Explicit goals, completion criteria, and success metrics
- Optional: Proposed folder hierarchy, task execution roadmap, or prompt orchestration schema
Persistent Learning & Memory Encoding
Use MCP-backed memory tools to capture strategic outcomes:
- Principle extraction and reframing
- Canonical prompt structures and schema definitions
- Decisions and their causal rationales
Structure this using:
mcp_memory_create_entitiesfor capturing first-order insightsmcp_memory_add_observationsto log evolution or iteration tracesmcp_memory_create_relationsto encode semantic lineage and dependency graphs
Model Output Format (Preferred for Executive Contexts)
### Recommendation 1: Template Classification Layer
**Description:** Implement deterministic pre-parsing logic to fingerprint invoice template variants using invariant keywords and structural cues. Route input accordingly to specialized parsing handlers.
**Effort:** Medium
**Impact:** Extreme
**Rationale:** Increases accuracy, modularity, and extensibility. Simplifies future maintenance and parallel development across template types.
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.
- 4d ago First seen · 77 lines · 543 tokens per session scan A f4eb356614cd
001-philosophers-stone is a cursor rule published in the GitHub repository hamzaamjad/cursor-rules (2 stars, last pushed 1y ago), licensed MIT. It adds 543 tokens to every session, about $0.0027 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
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
Context Recorder System (记录员系统) - 模块化索引文件.
memsprout
Cursor rule "memsprout" from memsprout/agents, covering using memsprout, search first, capturing, spaces and topics and files.