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/bia-technologies/yaxunit/reflection-intermediategit clone --depth 1 https://github.com/bia-technologies/yaxunitWhat 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 | $0.00000 | $0.01045 |
| Opus 5 | $0.00000 | $0.00522 |
| Sonnet 5 | $0.00000 | $0.00209 |
| Haiku 4.5 | $0.00000 | $0.00104 |
Grade A, and why
reflection-intermediate 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 today.
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 — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
LEVEL 3 REFLECTION: INTERMEDIATE FEATURE REVIEW
TL;DR: This guide structures the reflection process for a completed Level 3 intermediate feature. The focus is on a detailed review of the entire feature development lifecycle, from planning and design through implementation and testing, to extract meaningful lessons and identify improvements for future feature work.
🔍 Level 3 Reflection Process
The goal is to create a comprehensive memory-bank/reflection/reflection-[feature_id].md document.
graph TD
StartReflect["Start L3 Reflection"] -->
ReviewDocs["1. Review All Gathered Documentation"] -->
AssessOutcome["2. Assess Overall Feature Outcome<br>Did it meet all requirements from tasks.md? Was it successful?"] -->
AnalyzePlan["3. Analyze Planning Phase Effectiveness<br>Was planning-comprehensive.mdc guidance effective? Was the plan accurate? Scope creep?"] -->
AnalyzeCreative["4. Analyze Creative Phase(s) Effectiveness<br>Were design decisions sound? Did they translate well to implementation? Issues?"] -->
AnalyzeImpl["5. Analyze Implementation Phase<br>What went well? Challenges? Bottlenecks? Adherence to design/style guide?"] -->
AnalyzeTesting["6. Analyze Testing Phase<br>Were tests adequate? Bugs found post-release (if applicable)? Test coverage feel right?"] -->
IdentifyLessons["7. Identify Key Lessons Learned<br>(Technical, Process, Teamwork, Estimation)"] -->
ProposeImprovements["8. Propose Actionable Improvements<br>For future L3 feature development"] -->
DraftReflectionDoc["9. Draft `reflection-[feature_id].md`<br>Using structured template"] -->
FinalizeReflection["10. Finalize & Save Reflection Document"] -->
UpdateTasksStatus["11. Update `tasks.md`<br>Mark L3 Reflection Complete"] -->
ReflectionDone["L3 Reflection Complete<br>Ready for ARCHIVE Mode"]
style StartReflect fill:#ba68c8,stroke:#9c27b0
style ReflectionDone fill:#d1c4e9,stroke:#b39ddb
📝 Structure for memory-bank/reflection-[feature_id].md
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.
- today First seen · 75 lines · 0 tokens per session scan A 4f8f7200cab2
reflection-intermediate is a cursor rule published in the GitHub repository bia-technologies/yaxunit (322 stars, last pushed 2mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 1,045 tokens. 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 2026-09-01.
Other cursor rules, from other repositories
cursorrules
CLAUDE.md.
telegram-bot-tests
Test conventions for Telegram Bot library.
1c-coding-standards
Стандарты кода BSL: именование, запросы, коллекции.
1c-skd-two-pass-preprocessing
Двухпроходный СКД: предобработка детальных записей до свертки.
model-selection
Стратегия выбора моделей: Opus/Sonnet/Haiku по типу задачи.
zpa-dependency-chain
ZPA application onboarding requires resources to be created in a specific dependency order. Skipping dependencies causes cryptic 400 errors.