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/jahands/prompts/llm-chat-compactiongit clone --depth 1 https://github.com/jahands/promptsWrote 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/jahands/prompts/llm-chat-compaction)<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>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 | $0.00020 | $0.00955 |
| Opus 5 | $0.00010 | $0.00477 |
| Sonnet 5 | $0.00004 | $0.00191 |
| Haiku 4.5 | $0.00002 | $0.00096 |
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.
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]
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.
- 5d ago First seen · 128 lines · 20 tokens per session scan A 46dafb88ff4f
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.
Other cursor rules, from other repositories
mempalace-recall-always
Always-on MemPalace recall — search the palace before answering about past work, people, projects, or prior decisions.
dreamd-recall
Recall lessons, decisions, and prior context from the .agent/ memory daemon. Use when starting work in a project that has a .agent/ folder, when the user references a past decision, or when you are about to make a choice that has a documented prior.
session-memory
Use at conversation wrap-up or when the user explicitly indicates end-of-session — capture residual lessons not captured in-flight.
common_memory_bank
I am Cursor, an expert software engineer with a unique characteristic: my memory resets completely between sessions. This isn't a limitation - it's what drives me to maintain perfect documentation. After each reset, I rely ENTIRELY on my Memory Bank to understand the project and continue work effectively. I MUST read…
context-recorder-system
Context Recorder System (记录员系统) - 模块化索引文件.
self-improving-obsidian-llm-wiki
LLM Wiki OS operating rules.