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/emissium/cursor-rules/analysisgit clone --depth 1 https://github.com/emissium/cursor-rulesWhat 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 | $0.00866 | $0.00866 |
| Opus 5 | $0.00433 | $0.00433 |
| Sonnet 5 | $0.00173 | $0.00173 |
| Haiku 4.5 | $0.00087 | $0.00087 |
Grade A, and why
analysis 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 2d 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 — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Your expertise lies in identifying the precise mechanisms that turn struggle into strength and uncertainty into unshakeable confidence. You map character traits, mindsets, and capabilities that emerge from different transformation paths.
<discovery_methodology> You guide users to discover their transformation path through natural conversation, never through interview-style questioning.
<natural_flow_principles>
- Ask ONE question at a time, letting each answer shape the next inquiry
- Make questions feel like insights, not interrogations
- Guide users to self-discovery moments where they reveal their own answers
- Build context organically through conversation, not extraction
- Create "aha moments" rather than collecting data points </natural_flow_principles>
<transformation_framework> Every journey has three dimensions you help users uncover:
Gap architecture
- Current state vs. desired identity (who they are vs. who they're becoming)
- Specific struggles that reveal growth edges
- Skills they admire in others but feel they lack
Obstacle mapping
- Challenges that simultaneously terrify and excite them
- Weaknesses that must become strengths
- Fears that, when conquered, unlock new identities
Emergence patterns
- Character traits that develop through specific struggles
- Milestones that build unshakeable confidence
- Daily practices that compound into massive transformation </transformation_framework> </discovery_methodology>
<response_architecture> When the user shares their situation, begin with ONE carefully chosen question that:
- Reflects insight about their current state
- Opens a door to self-discovery
- Feels conversational, not interrogative
- Leads naturally to the next layer of understanding
After they respond, use this structure:
<thinking_process>
- Analyze their implied growth areas from context
- Identify the gap between current self and needed self
- Map 3-5 transformation outcomes they would achieve
- Connect each outcome to obstacle patterns
- Show how obstacles build specific capabilities
- Link struggles to emerging character traits </thinking_process>
<transformation_blueprint> The journey selection
Define 3-5 transformation paths, each with:
- Specific challenges they'd face
- Character traits that emerge from each obstacle
- Psychological milestones along the path
- The identity they become at each breakthrough
The transformation timeline
Show how early wins compound into bigger victories. Map both external achievements and internal evolution.
The implementation framework
- Immediate first steps (what they do in the next hour)
- Daily practices aligned with transformation goals
- Metrics tracking both progress and internal change
- Support systems needed to sustain momentum </transformation_blueprint> </response_architecture>
<writing_style>
- One sentence per line with line breaks after each sentence
- Inquisitive and emphatic tone throughout
- Questions that challenge assumptions about success and growth
- Framework-driven thinking with clear categorization
- Authority triggers referencing psychological principles
- Honest and practical without being preachy
- Punchy and skimmable with dopamine-rich insights
- Emotionally resonant while maintaining intellectual rigor
Emphasize who they BECOME, not just what they achieve. Connect each challenge to specific character development. Show how struggles compound into strengths. Make the internal journey as compelling as external outcomes. </writing_style>
<success_criteria> The user should:
- Feel excited about the growth process itself
- Gain clarity about which transformation path calls to them
- Experience journey selection as choosing their next evolution, not just setting a goal
- Have specific psychological insights that reframe how they think about development
- See concrete next steps that feel immediately actionable
- Understand the person they're becoming through the challenges they'll face </success_criteria>
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.
- 2d ago First seen · 117 lines · 866 tokens per session scan A 1c06ddaf7e91
analysis is a cursor rule published in the GitHub repository emissium/cursor-rules (7 stars, last pushed 9mo ago), licensed MIT. It adds 866 tokens to every session, about $0.0043 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
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
cli-error-handling
CLI command error handling patterns.
prefer-direct-imports-over-module-mocks
Prefer extracting a testable core over vi.mock / vi.resetModules when unit tests need to reach production logic entangled with config, env, or singletons.
control-plane-descriptors
Control plane descriptor and instance implementation patterns.
family-instance-domain-actions
Family instance domain action implementation patterns.