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/alkoleft/platform-context-exporterWrote 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/alkoleft/platform-context-exporter/complexity-decision-tree)<a href="https://agentmods.dev/rules/alkoleft/platform-context-exporter/complexity-decision-tree"><img src="https://agentmods.dev/badge/rules/alkoleft/platform-context-exporter/complexity-decision-tree/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/alkoleft/platform-context-exporter/complexity-decision-tree"><img src="https://agentmods.dev/badge/rules/alkoleft/platform-context-exporter/complexity-decision-tree.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 | $0.01652 |
| Opus 5.5 | $0.00000 | $0.00661 |
| Sonnet 5.5 | $0.00000 | $0.00330 |
| Haiku 4.5 | $0.00000 | $0.00165 |
Grade A, and why
complexity-decision-tree 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.
This is a copy
100% identical to complexity-decision-tree — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 188 lines — stays where its author put it; the contents beside it link to each section on GitHub.
TASK COMPLEXITY DETERMINATION
TL;DR: This document helps determine the appropriate complexity level (1-4) for any task. Use the decision tree and indicators to select the right process level, then load the corresponding process map.
🌳 COMPLEXITY DECISION TREE
graph TD
Start["New Task"] --> Q1{"Bug fix or<br>error correction?"}
Q1 -->|Yes| Q1a{"Affects single<br>component?"}
Q1a -->|Yes| L1["Level 1:<br>Quick Bug Fix"]
Q1a -->|No| Q1b{"Affects multiple<br>components?"}
Q1b -->|Yes| L2["Level 2:<br>Simple Enhancement"]
Q1b -->|No| Q1c{"Affects system<br>architecture?"}
Q1c -->|Yes| L3["Level 3:<br>Intermediate Feature"]
Q1c -->|No| L2
Q1 -->|No| Q2{"Adding small<br>feature or<br>enhancement?"}
Q2 -->|Yes| Q2a{"Self-contained<br>change?"}
Q2a -->|Yes| L2
Q2a -->|No| Q2b{"Affects multiple<br>components?"}
Q2b -->|Yes| L3
Q2b -->|No| L2
Q2 -->|No| Q3{"Complete feature<br>requiring multiple<br>components?"}
Q3 -->|Yes| Q3a{"Architectural<br>implications?"}
Q3a -->|Yes| L4["Level 4:<br>Complex System"]
Q3a -->|No| L3
Q3 -->|No| Q4{"System-wide or<br>architectural<br>change?"}
Q4 -->|Yes| L4
Q4 -->|No| L3
L1 --> LoadL1["Load Level 1 Map"]
L2 --> LoadL2["Load Level 2 Map"]
L3 --> LoadL3["Load Level 3 Map"]
L4 --> LoadL4["Load Level 4 Map"]
📊 COMPLEXITY LEVEL INDICATORS
Use these indicators to help determine task complexity:
Level 1: Quick Bug Fix
- Keywords: "fix", "broken", "not working", "issue", "bug", "error", "crash"
- Scope: Single component or UI element
- Duration: Can be completed quickly (minutes to hours)
- Risk: Low, isolated changes
- Examples:
- Fix button not working
- Correct styling issue
- Fix validation error
- Resolve broken link
- Fix typo or text issue
Level 2: Simple Enhancement
- Keywords: "add", "improve", "update", "change", "enhance", "modify"
- Scope: Single component or subsystem
- Duration: Hours to 1-2 days
- Risk: Moderate, contained to specific area
- Examples:
- Add form field
- Improve validation
- Update styling
- Add simple feature
- Change text content
- Enhance existing component
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 · 188 lines · 0 tokens per session scan A b15263400b63
complexity-decision-tree is a cursor rule published in the GitHub repository alkoleft/platform-context-exporter (49 stars, last pushed 1y ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,652 tokens. A static security scan graded it A with 0 findings. It is 100% identical to complexity-decision-tree, differing in 0 lines, and is treated as a copy.
Other cursor rules, from other repositories
1c-coding-standards
Coding standards for BSL, the programming language used by the 1C business software platform. They cover naming, method documentation, database queries, collections, client-server code, and performance practices.
code-review-checklist
A code-review checklist for 1C source files, including BSL and OS files. It groups findings by severity and checks issues such as security, performance, errors, access control, duplication, and maintainability.
bsl-ssl
A set of rules for developing 1C applications built on БСП, the Russian-language Standard Subsystems Library. It tells developers when to reuse library functionality, how to mark changes, and how to handle outdated objects.
1c-report-direct-query
A 1C reporting rule that runs the report query directly instead of using the standard data-composition engine (СКД). It then displays or exports the returned table manually.
1c-transactions-and-locks
Guidance for using transactions and controlled locks in 1C, where a transaction groups database changes so they can be accepted or cancelled together. It also explains the order in which locks should be taken when several operations share data.
query-optimization-tips
A set of tips for making 1C database queries run faster. 1C is a business software platform, and these rules cover query writing and review.