Conversation Management

Conversation Management is a skill for Claude Code, Codex from llaa33219/casabot. It costs 13 tokens per session (1,173 once invoked), scanned A, original, Apache-2.0.

A manual for managing chat sessions, their automatically saved history, and connections to outside services.

In plain words
What is it for?
Creating, viewing, searching, and integrating conversation sessions using the CasAbot history system.
Why use it?
It explains where conversations are stored and how to find or inspect them after a session ends.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions subagents.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is podman exec -d webhook-bridge node /workspace/webhook-server.js.

Good fit Creating, viewing, searching, and integrating conversation sessions using the CasAbot history system.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/llaa33219/casabot
agentmods
npx agentmods add skills/llaa33219/casabot/chat

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 Management

README.md
[![agentmods](https://agentmods.dev/badge/skills/llaa33219/casabot/chat/github.svg)](https://agentmods.dev/skills/llaa33219/casabot/chat)
Your own site
<a href="https://agentmods.dev/skills/llaa33219/casabot/chat"><img src="https://agentmods.dev/badge/skills/llaa33219/casabot/chat/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 Management

Your own site · 80×15
<a href="https://agentmods.dev/skills/llaa33219/casabot/chat"><img src="https://agentmods.dev/badge/skills/llaa33219/casabot/chat.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 13 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,173 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 $0.00013 $0.01173
Opus 5.5 $0.00005 $0.00469
Sonnet 5.5 $0.00003 $0.00235
Haiku 4.5 $0.00001 $0.00117

Measured 2mo ago against content hash a2f61802d791, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

Conversation Management 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 2mo 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/chat/SKILL.md · 166 lines

How it starts

The opening of the file, as written. The whole thing — 166 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Conversation Management

This manual explains how to create, view, and search conversation sessions, and how to integrate with external services.


1. Session Management

Session Structure

Each conversation session is automatically saved as a JSON file in the ~/casabot/history/ directory.

{
  "id": "unique session ID",
  "startedAt": "2024-01-15T09:30:00.000Z",
  "messages": [
    {
      "role": "user | assistant | system | tool",
      "content": "message content",
      "toolCalls": [],
      "toolCallId": ""
    }
  ]
}

Session Lifecycle

  • Creation: A new session is automatically created when you run the casabot command.
  • Persistence: Messages are automatically appended as the conversation progresses.
  • Termination: The session closes when the program exits.
  • Preservation: Logs are permanently preserved in the history directory after termination.

2. Loading Conversations

View recent conversation list

# Recent 20 conversations (newest first)
ls -lt ~/casabot/history/ | head -20

# Check filenames and sizes
ls -lhS ~/casabot/history/

View specific conversation

# View full conversation (formatted)
cat ~/casabot/history/<conversation-id>.json | jq '.messages[] | {role, content: .content[:100]}'

# View only user messages
cat ~/casabot/history/<conversation-id>.json | jq '.messages[] | select(.role == "user") | .content'

# View only assistant responses
cat ~/casabot/history/<conversation-id>.json | jq '.messages[] | select(.role == "assistant") | .content'

Check session metadata

# Session ID and start time
cat ~/casabot/history/<conversation-id>.json | jq '{id, startedAt, messageCount: (.messages | length)}'

3. Searching Previous Conversations

Search by keyword

# Search all conversations for a keyword
grep -rl "keyword" ~/casabot/history/

# View context of conversations containing the keyword
grep -l "keyword" ~/casabot/history/*.json | while read f; do
  echo "=== $(basename $f) ==="
  cat "$f" | jq '.messages[] | select(.content | contains("keyword")) | {role, content: .content[:200]}'
done

Read the full file on GitHub · 166 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. 2mo ago First seen · 166 lines · 13 tokens per session scan A a2f61802d791

Subscribe to this mod's changes

Conversation Management is a skill published in the GitHub repository llaa33219/casabot (5 stars, last pushed 8mo ago), licensed Apache-2.0. It adds 13 tokens to every session and 1,173 once invoked, about $0.0001 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 2026-08-31.

Related

Conversation Management compared with skills from other repositories

Conversation Management next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
Conversation Managementllaa33219/casabotSkill58mo agoApache-2.0A13Claude Code, Codex
orbit-notionnexu-io/open-designSkill106kyesterdayApache-2.0A117Claude Code, Codex
agentmailpaperclipai/paperclipSkill111kyesterdayMITA30Claude Code, Codex
Cortexdanielmiessler/LifeOSSkill20kyesterdayMITA184Claude Code
rowboat-spacesrowboatlabs/rowboatSkill18kyesterdayApache-2.0A60Claude Code, Codex
feishuHmbown/CodeWhaleSkill41k6d agoMITA33Claude Code, Codex
pinchtab-mcppinchtab/pinchtabSkill11k10d agoMITA52Claude Code, Codex