reflection-format

A required four-part review of completed work: successes, challenges, lessons learned, and improvements for next time.

In plain words
What is it for?
Writing structured post-task notes that capture technical decisions, difficulties, solutions, and future improvements.
Why use it?
It gives every task a consistent way to record what happened and what should change. The specific item requirements help avoid vague reflections.

Cursor rule for Cursor

Install

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.

agentmods
npx agentmods add rules/kfnzero/mantis-mcp-server/reflection-format
Clone the repo
git clone --depth 1 https://github.com/kfnzero/mantis-mcp-server

Made for: Cursor.

Per session 579 This file is loaded in full into every session.
When invoked 579 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 2d ago against content hash 3186530e5564, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

.cursor/rules/Core Implementation/reflection-format.mdc · 89 lines

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:

  1. What Went Well

    • Include ≥3 specific successes
    • Focus on technical details that worked
    • Mention effective decisions
    • Use concrete examples
  2. Challenges

    • Include ≥2 specific challenges
    • Describe how each was addressed
    • Be honest about difficulties
    • Note solutions implemented
  3. Lessons Learned

    • Include ≥3 specific insights
    • Focus on technical learnings
    • Include both positive and negative
    • Note knowledge for future tasks
  4. 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

Read the full file on GitHub · 89 lines

Changes

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.

  1. 2d ago First seen · 89 lines · 579 tokens per session scan A 3186530e5564

Subscribe to this mod's changes

reflection-format is a cursor rule published in the GitHub repository kfnzero/mantis-mcp-server (10 stars, last pushed 12mo 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. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.