paleo-converse

paleo-converse is a skill for Claude Code from mocasus/paleo. It costs 82 tokens per session (414 once invoked), scanned A, original, MIT.

A conversation-compression rule for shortening earlier chat messages while retaining recent messages.

In plain words
What is it for?
Use it to condense a long session, merge repeated requests, or keep only the latest several turns in full.
Why use it?
It reduces the amount of chat history the agent must process without losing decisions, commands, paths, or unresolved questions.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the paleo plugin — 7 skills shipped together

Good fit Use it to condense a long session, merge repeated requests, or keep only the latest several turns in full.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/mocasus/paleo/paleo-converse
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 mocasus/paleo --skill paleo-converse
Clone the repo
git clone --depth 1 https://github.com/mocasus/paleo

Made for: Claude Code.

Or install paleo, the plugin that ships this one along with the rest of its 7 skills.

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 paleo-converse

README.md
[![agentmods](https://agentmods.dev/badge/skills/mocasus/paleo/paleo-converse/github.svg)](https://agentmods.dev/skills/mocasus/paleo/paleo-converse)
Your own site
<a href="https://agentmods.dev/skills/mocasus/paleo/paleo-converse"><img src="https://agentmods.dev/badge/skills/mocasus/paleo/paleo-converse/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 paleo-converse

Your own site · 80×15
<a href="https://agentmods.dev/skills/mocasus/paleo/paleo-converse"><img src="https://agentmods.dev/badge/skills/mocasus/paleo/paleo-converse.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 82 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 414 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 $0.00082 $0.00414
Opus 5 $0.00041 $0.00207
Sonnet 5 $0.00016 $0.00083
Haiku 4.5 $0.00008 $0.00041

Measured 10d ago against content hash 68d429e2a393, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

paleo-converse 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 10d 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.

skills/paleo-converse/SKILL.md · 36 lines

What it actually says

paleo-converse

Conversation compression. Shrink old turns, keep recent verbatim.

Rules

  • Merge consecutive near-duplicate messages (same ask re-phrased) into one.
  • Condense turns older than the last N (default 6) into a tight summary: goals, decisions, open questions, key values.
  • Keep the last N turns verbatim — do not rewrite the user's most recent intent.
  • Preserve: file paths, commands, IDs, code snippets, error strings, decisions.
  • Drop: chit-chat, repeated confirmations, "ok great thanks", filler.
  • Never summarize away the current task or a pending question.

Levels

  • lite: merge duplicates only, keep all turns.
  • full (default): merge + condense turns older than N.
  • ultra: condense everything older than the last 3 turns.

Switch

  • paleo-converse / condense chat on. stop condensing / keep full history off.
  • paleo-converse N=8 sets the retained verbatim window.

Gotchas

  • Don't compress the turn you're acting on — only history.
  • If the user references "what we said earlier" ambiguously, keep a bit more context.
  • High-stakes (legal/spec/config review): keep exact quotes.
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. 10d ago First seen · 36 lines · 82 tokens per session scan A 68d429e2a393

Subscribe to this mod's changes

paleo-converse is a skill published in the GitHub repository mocasus/paleo (20 stars, last pushed 1mo ago), licensed MIT. It adds 82 tokens to every session and 414 once invoked, about $0.0004 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.

Related

Other skills, from other repositories

hermes-context-optimization

Use this when the user asks about Hermes prompt/context size, “hello” startup cost, compression behavior, memory/profile bloat, tool-schema overhead, skill loading, session-store/search-index storage, or multimodal/visual-context approaches such as Snapcompact.

AtlasOmnia/donna-starter · 35 tokens

hermes-mnemosyne

Mnemosyne is Hermes' primary local-first memory engine — SQLite with vector + FTS5 hybrid search, 19+ tools, auto-consolidation, and a standalone CLI. It's a pip-installed plugin (not a built-in toolset) discovered via $HERMESHOME/plugins/mnemosyne/.

AtlasOmnia/donna-starter · 30 tokens

hermes-session-maintenance

Use this skill when the user asks about pruning Hermes sessions, session retention, session DB size, hermes sessions prune, sessions.autoprune, sessions.retentiondays, session export/backup, or whether old conversations should be capped.

AtlasOmnia/donna-starter · 37 tokens

memory-init

Scaffold a project-local memory directory and AGENTS.md guidance for reusable agent knowledge. Use when a user wants to initialize .agents/memories/ or another project memory path so future agents can read and maintain durable project context.

flc1125/skills · 50 tokens

mnemosyne-maintenance

Use when: upgrading Mnemosyne, diagnosing slow/hung consolidation (mnemosynesleep), fixing missing embeddings, or troubleshooting import/version mismatches.

AtlasOmnia/donna-starter · 40 tokens

obsidian-memory-architecture

Use when designing, setting up, or maintaining an Obsidian vault as Hermes Agent's durable knowledge layer. Routes facts, conversation history, documents, procedures, and daily logs to the correct Hermes or vault system without duplicating everything into the prompt.

AtlasOmnia/hermes-custom-pack · 56 tokens