conversation-compaction

conversation-compaction is a skill for Claude Code, Codex from Prismer-AI/PrismerCloud. It costs 139 tokens per session (1,474 once invoked), scanned A, original, MIT.

A process that creates a shorter working view of older conversation messages by pointing to existing durable memory pages and retaining facts that have no matching page.

In plain words
What is it for?
Use it when a long conversation moves older messages out of the recent context and the agent needs a compact reference to earlier decisions and facts.
Why use it?
It keeps aging conversations usable without repeatedly rewriting facts already stored in memory or pretending the process itself saves durable memory.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it when a long conversation moves older messages out of the recent context and the agent needs a compact reference to earlier decisions and facts.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/prismer-ai/prismercloud/conversation-compaction
About the project

Prismer Cloud is an infrastructure layer for AI agents that provides shared learning, compressed context, persistent memory, collaboration, messaging, tasks, identity, and workspaces. It is for agents and the people building or using long-running agent systems that need information and outcomes to persist across sessions. The catalogue entries provide skills, hooks, agents, instructions, and a plugin for using Prismer Cloud.

Prismer-AI/PrismerCloud · 1,384 stars · on GitHub · prismer.cloud

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.

Any agent
npx skills add Prismer-AI/PrismerCloud --skill conversation-compaction
Clone the repo
git clone --depth 1 https://github.com/Prismer-AI/PrismerCloud

Made for: Claude Code, Codex.

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 conversation-compaction

README.md
[![agentmods](https://agentmods.dev/badge/skills/prismer-ai/prismercloud/conversation-compaction/github.svg)](https://agentmods.dev/skills/prismer-ai/prismercloud/conversation-compaction)
Your own site
<a href="https://agentmods.dev/skills/prismer-ai/prismercloud/conversation-compaction"><img src="https://agentmods.dev/badge/skills/prismer-ai/prismercloud/conversation-compaction/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for conversation-compaction

Your own site · 80×15
<a href="https://agentmods.dev/skills/prismer-ai/prismercloud/conversation-compaction"><img src="https://agentmods.dev/badge/skills/prismer-ai/prismercloud/conversation-compaction.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 139 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,474 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00139 $0.01474
Opus 5.5 $0.00056 $0.00590
Sonnet 5.5 $0.00028 $0.00295
Haiku 4.5 $0.00014 $0.00147

Measured 19d ago against content hash cb630cca1067, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

conversation-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 19d 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.

sdk/cloud/catalog/skills/conversation-compaction/SKILL.md · 118 lines

How it starts

The opening of the file, as written. The whole thing — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Conversation Compaction — memory's session projection

You are producing the session projection of a slice of an aging conversation (messages that scrolled past the recent verbatim window). The projection replaces the raw slice in future agent context.

The model — sync by POINTER, not by re-summary

Durable knowledge lives in memory (the memory skill owns it). A session projection does not re-summarize durable facts — it points at the memory pages that hold them, NOT by you re-deriving what memory already knows.

How this runs (important): you execute as a SINGLE model call inside the agent's daemon (mirroring the memory extract post-turn hook) — you have no live memory tools to browse/write. Durable capture to memory is the extract hook's job (it runs alongside you every turn). Your input carries the memory pages you need: <existing-memory-pages> (recall-found). You MATCH durable facts to those pages and emit POINTERS; you do not write memory yourself.

Your job over a slice is only:

① for each slice message:
     durable + matches a provided page  → emit a memoryRefs POINTER (path + note)
     durable + NO page matches          → inline into summary (degraded; extract will capture it)
     ephemeral                          → carry THIN in the digest (ages out)
     noise                              → DROP
② emit — the thin ephemeral digest + POINTERS to every matched page

Input you receive

  • slice: the raw messages, oldest first, each [msgId] @username (role): text.
  • conversationType: group | direct.
  • <existing-memory-pages>: pages found by DEVICE-LOCAL recall over this slice that may already hold durable facts from it (a fuzzy match, not an exact raw→page mapping).

Pointer-first rule (recall-fed)

You are given <existing-memory-pages> (pages recall thinks already hold durable facts from this slice). For a durable fact in the slice that matches an existing page, emit a memoryRefs pointer { path, note } — do not restate it in summary. Only inline a durable fact into summary (degraded) when no existing page matches it.

Read the full file on GitHub · 118 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. 19d ago First seen · 118 lines · 139 tokens per session scan A cb630cca1067

Subscribe to this mod's changes

conversation-compaction is a skill published in the GitHub repository Prismer-AI/PrismerCloud (1,384 stars, last pushed 3d ago), licensed MIT. It adds 139 tokens to every session and 1,474 once invoked, about $0.0006 per session on Opus 5.5. 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 2026-09-29.