llm-chat-compaction

llm-chat-compaction is a cursor rule for coding agents from jahands/prompts. It costs 20 tokens per session (955 once invoked), scanned A, original, MIT.

Guidelines for shortening a long AI chat while keeping its important context. The summary records decisions, code changes, problems, current status, and next steps.

In plain words
What is it for?
Summarising development conversations before starting a new thread. Preserving the reasoning and unfinished work behind code changes.
Why use it?
It prevents key information from being lost when a conversation becomes too long or moves to a new thread. It also reduces the amount of text the AI must process.

Cursor rule

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/jahands/prompts/llm-chat-compaction
Clone the repo
git clone --depth 1 https://github.com/jahands/prompts

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 llm-chat-compaction

README.md
[![agentmods](https://agentmods.dev/badge/rules/jahands/prompts/llm-chat-compaction.svg)](https://agentmods.dev/rules/jahands/prompts/llm-chat-compaction)
Your own site
<a href="https://agentmods.dev/rules/jahands/prompts/llm-chat-compaction"><img src="https://agentmods.dev/badge/rules/jahands/prompts/llm-chat-compaction.svg" alt="Measured on agentmods" height="20"></a>
Per session 20 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 955 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 $0.00020 $0.00955
Opus 5 $0.00010 $0.00477
Sonnet 5 $0.00004 $0.00191
Haiku 4.5 $0.00002 $0.00096

Measured 5d ago against content hash 46dafb88ff4f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

llm-chat-compaction 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 5d 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.

cursor-rules/llm-chat-compaction.mdc · 128 lines

How it starts

The opening of the file, as written. The whole thing — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.

When chat threads become too long or need to be copied to a new thread, compact them to preserve essential context while reducing token usage. The XML tags here are delimiters for guidance—do not reproduce them in the generated summary.

Decisions Made • [Decision 1 with brief rationale] • [Decision 2 with brief rationale]

Code Changes

[Component/File Name]

Before:

[relevant code snippet]

After:

[updated code snippet]

Issues Encountered and Resolved • Issue: [description] Resolution: [what fixed it]

Current State • [What’s working] • [What still needs attention] • [Next steps if any]

Read the full file on GitHub · 128 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. 5d ago First seen · 128 lines · 20 tokens per session scan A 46dafb88ff4f

Subscribe to this mod's changes

llm-chat-compaction is a cursor rule published in the GitHub repository jahands/prompts (19 stars, last pushed 7mo ago), licensed MIT. It adds 20 tokens to every session and 955 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 2026-08-30.