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/savagelysubtle/big-brain-memory-bank/reflection-formatgit clone --depth 1 https://github.com/savagelysubtle/BIG-BRAIN-Memory-BankWrote 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/savagelysubtle/big-brain-memory-bank/reflection-format)<a href="https://agentmods.dev/rules/savagelysubtle/big-brain-memory-bank/reflection-format"><img src="https://agentmods.dev/badge/rules/savagelysubtle/big-brain-memory-bank/reflection-format.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 | $0.00579 | $0.00579 |
| Opus 5 | $0.00290 | $0.00290 |
| Sonnet 5 | $0.00116 | $0.00116 |
| Haiku 4.5 | $0.00058 | $0.00058 |
Grade A, and why
reflection-format 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 3d 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-format — 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 — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
REFLECTION FORMAT
TL;DR: Every task requires a reflection with four specific sections: What Went Well (≥3 items), Challenges (≥2 items), Lessons Learned (≥3 items), and Improvements for Next Time (≥3 items). Be specific and detailed, not generic.
📝 REFLECTION STRUCTURE
Always use this exact structure:
## REFLECTION
### What Went Well
- [Specific success 1]
- [Specific success 2]
- [Specific success 3]
### Challenges
- [Specific challenge 1]
- [Specific challenge 2]
### Lessons Learned
- [Specific lesson 1]
- [Specific lesson 2]
- [Specific lesson 3]
### Improvements for Next Time
- [Specific improvement 1]
- [Specific improvement 2]
- [Specific improvement 3]
📊 SECTION REQUIREMENTS
Each section has specific requirements:
-
What Went Well
- Include ≥3 specific successes
- Focus on technical details that worked
- Mention effective decisions
- Use concrete examples
-
Challenges
- Include ≥2 specific challenges
- Describe how each was addressed
- Be honest about difficulties
- Note solutions implemented
-
Lessons Learned
- Include ≥3 specific insights
- Focus on technical learnings
- Include both positive and negative
- Note knowledge for future tasks
-
Improvements for Next Time
- Include ≥3 specific improvements
- Be concrete about future approaches
- Focus on actionable changes
- Note process improvements
🔍 SPECIFICITY GUIDE
❌ Too Vague (Avoid)
- "The code works well"
- "There were some challenges"
- "Testing could be improved"
✅ Properly Specific
- "The modular component architecture allowed for easy unit testing"
- "Initial performance issues with the data filtering algorithm required optimization using memoization"
- "Implementing a more detailed technical specification phase would clarify edge cases before coding"
✓ REFLECTION CHECKPOINTS
Before completing a reflection, verify:
- All four sections included with exact headings
- "What Went Well" has ≥3 specific items
- "Challenges" has ≥2 specific items
- "Lessons Learned" has ≥3 specific items
- "Improvements for Next Time" has ≥3 specific items
- Content is specific and detailed
- Sections are in the correct order
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.
- 3d ago First seen · 89 lines · 579 tokens per session scan A 3186530e5564
reflection-format is a cursor rule published in the GitHub repository savagelysubtle/BIG-BRAIN-Memory-Bank (5 stars, last pushed 1y ago), licensed MIT. It adds 579 tokens to every session, about $0.0029 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to reflection-format, differing in 0 lines, and is treated as a copy.
Other cursor rules, from other repositories
wrapup
End-of-session wrap-up: summarizes the session and pushes a log to the project's linked NotebookLM notebook. Activate with @wrapup in chat, or "wrap up", "save this session", or "end of session".
memory-bank
You are an expert software engineer with a unique characteristic: your memory resets completely between sessions. This isn't a limitation - it's what drives you to maintain perfect documentation. At the beginning of each dialogue, you rely ENTIRELY on your Memory Bank to understand the project and continue work…
composer-coding-excellence
Coding craft — surgical edits, convention matching, no scope creep, no slop comments, no fabricated APIs.
composer-core
Always-on builder spine — continue the app, demoable slice, Build loop, Run/Wired handoff, ask only on high confusion weight.
clarify-first
Infer-and-act by default — ask only on high confusion weight, after inspecting, with a decision-linked question.
memory-protocol
记忆系统 — 召回、写入、维护、防丢失的完整协议.