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/alkoleft/platform-context-exporter/reflection-comprehensivegit clone --depth 1 https://github.com/alkoleft/platform-context-exporterWhat 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 | $0.06108 | $0.06108 |
| Opus 5 | $0.03054 | $0.03054 |
| Sonnet 5 | $0.01222 | $0.01222 |
| Haiku 4.5 | $0.00611 | $0.00611 |
Grade A, and why
reflection-comprehensive 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.
This is a copy
100% identical to reflection-comprehensive — 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 — 719 lines — stays where its author put it; the contents beside it link to each section on GitHub.
description: Comprehensive reflection format for Level 4 Complex System tasks globs: "/level4/", "/reflection/" alwaysApply: false
COMPREHENSIVE REFLECTION FOR LEVEL 4 TASKS
TL;DR: This document outlines a structured, comprehensive approach to reflection for Level 4 (Complex System) tasks, including system review, success and challenge analysis, strategic insights, and action planning.
🔍 COMPREHENSIVE REFLECTION OVERVIEW
Level 4 Complex System tasks require in-depth reflection to capture key insights, document successes and challenges, extract strategic lessons, and guide future improvements. This systematic reflection process ensures organizational learning and continuous improvement.
flowchart TD
classDef phase fill:#f9d77e,stroke:#d9b95c,color:#000
classDef artifact fill:#f4b8c4,stroke:#d498a4,color:#000
classDef verification fill:#c5e8b7,stroke:#a5c897,color:#000
Start([Begin Reflection<br>Process]) --> Template[Load Comprehensive<br>Reflection Template]
Template --> SysReview[Conduct System<br>Review]
SysReview --> ArchReview[Review Architecture<br>Decisions]
ArchReview --> ImplementReview[Review Implementation<br>Approach]
ImplementReview --> SuccessAnalysis[Document Successes<br>and Achievements]
SuccessAnalysis --> ChallengeAnalysis[Document Challenges<br>and Solutions]
ChallengeAnalysis --> Technical[Extract Technical<br>Insights]
Technical --> Process[Extract Process<br>Insights]
Process --> Business[Extract Business<br>Insights]
Business --> Strategic[Define Strategic<br>Actions]
Strategic --> Timeline[Analyze Timeline<br>Performance]
Timeline --> Documentation[Complete Reflection<br>Documentation]
Documentation --> Integration[Integrate with<br>Memory Bank]
Integration --> Verification{Reflection<br>Verification}
Verification -->|Pass| Complete([Reflection<br>Complete])
Verification -->|Fail| Revise[Revise<br>Reflection]
Revise --> Verification
Template -.-> RT((Reflection<br>Template))
SysReview -.-> SR((System<br>Review))
SuccessAnalysis & ChallengeAnalysis -.-> SCD((Success/Challenge<br>Document))
Technical & Process & Business -.-> Insights((Insight<br>Document))
Strategic -.-> Actions((Strategic<br>Actions))
class Start,Complete milestone
class Template,SysReview,ArchReview,ImplementReview,SuccessAnalysis,ChallengeAnalysis,Technical,Process,Business,Strategic,Timeline,Documentation,Integration step
class Verification verification
class RT,SR,SCD,Insights,Actions artifact
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 · 719 lines · 6,108 tokens per session scan A c6ac03ee88b3
reflection-comprehensive is a cursor rule published in the GitHub repository alkoleft/platform-context-exporter (48 stars, last pushed 1y ago), licensed MIT. It adds 6,108 tokens to every session, about $0.0305 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to reflection-comprehensive, differing in 0 lines, and is treated as a copy.
Other cursor rules, from other repositories
1c-coding-standards
Стандарты кода BSL: именование, запросы, коллекции.
anti_patterns
Критические антипаттерны 1С: запрос в цикле, реквизиты через точку.
bsl-ssl
Переиспользование БСП, разметка правок типовых модулей, устаревшие объекты.
edt-form-xml-requirements
Требования EDT к XML-формам (Form.form): extInfo, дефолты полей.
sdd-workflow
Specification-Driven Development: 9-фазный workflow разработки.
1c-report-direct-query
Прямой запрос в отчётах 1С (СКД) без схемы компоновки.