retrospective

retrospective is a cursor rule for Cursor from GoranErhartic/cursor-development-rules. It costs 22 tokens per session (178 once invoked), scanned A, original, MIT.

A review process for coding-agent rules after a task is finished. It records missing guidance, conflicts, and suggested improvements.

In plain words
What is it for?
Use it to review completed tasks and propose updates to rule files or an improvements log.
Why use it?
It helps teams find where their instructions failed to guide the work clearly.

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/goranerhartic/cursor-development-rules/retrospective
Clone the repo
git clone --depth 1 https://github.com/GoranErhartic/cursor-development-rules

Made for: Cursor.

Wrote 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.

agentmods badge for retrospective

README.md
[![agentmods](https://agentmods.dev/badge/rules/goranerhartic/cursor-development-rules/retrospective.svg)](https://agentmods.dev/rules/goranerhartic/cursor-development-rules/retrospective)
Your own site
<a href="https://agentmods.dev/rules/goranerhartic/cursor-development-rules/retrospective"><img src="https://agentmods.dev/badge/rules/goranerhartic/cursor-development-rules/retrospective.svg" alt="Measured on agentmods" height="20"></a>
Per session 22 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 178 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00022 $0.00178
Opus 5 $0.00011 $0.00089
Sonnet 5 $0.00004 $0.00036
Haiku 4.5 $0.00002 $0.00018

Measured yesterday against content hash 7c9cf4e48b66, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

retrospective 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 yesterday.

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.

.cursor/rules/retrospective.mdc · 28 lines

What it actually says

Agent Retrospective Protocol

End-of-Task Review

After completing any non-trivial task, evaluate:

  1. Rule Effectiveness - Did existing rules provide sufficient guidance?
  2. Gaps Encountered - What was unclear or missing?
  3. Contradictions - Did any rules conflict?
  4. Improvements - Specific suggestions for rule changes

Retrospective Format

Include in summary when applicable:

Rule Observations

  • Gap: [Description of missing guidance]
  • Contradiction: [Conflicting rules and how resolved]
  • Proposal: [Specific improvement suggestion]

Improvement File

Append significant findings to: .cursor/rules/IMPROVEMENTS.md

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. yesterday First seen · 28 lines · 22 tokens per session scan A 7c9cf4e48b66

Subscribe to this mod's changes

retrospective is a cursor rule published in the GitHub repository GoranErhartic/cursor-development-rules (19 stars, last pushed 6mo ago), licensed MIT. It adds 22 tokens to every session and 178 once invoked, about $0.0001 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 2026-09-03.