conversation-parser

A helper that reads exported conversations from ChatGPT, Claude, or similar tools and arranges them into topics with the speakers identified. It can also extract reasoning across several messages.

In plain words
What is it for?
Use it to process ChatGPT or Claude export files, or other message lists, into topic-organized content with speaker labels.
Why use it?
It removes the manual work of sorting a long conversation and working out who said what. The result is easier to review or use for later notes.

Agent

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 agents/datacore-one/datacore/conversation-parser
Clone the repo
git clone --depth 1 https://github.com/datacore-one/datacore
Per session 40 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,455 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 $0.00040 $0.01455
Opus 5 $0.00020 $0.00727
Sonnet 5 $0.00008 $0.00291
Haiku 4.5 $0.00004 $0.00145

Measured yesterday against content hash 33061b6c663d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

conversation-parser 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 yesterday.

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.

.datacore/agents/conversation-parser.md · 223 lines

How it starts

The opening of the file, as written. The whole thing — 223 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Conversation Parser

Engram Injection

Before starting work, load relevant learned patterns:

  1. Preferred: Call plur_admin MCP tool with action = "plur_inject_hybrid", prompt = your task description, scope = agent:conversation-parser
  2. Fallback: If MCP is unavailable, read .datacore/state/agent-engrams/conversation-parser.md for compiled engrams

Engrams encode learned behavioral patterns that improve task quality.

Agent Context

When to Reference This Agent

Called by: knowledge-extractor when input is a conversation export (JSON with message array structure)

Purpose: Parse dialogue exports into structured, topic-organized content with speaker attribution. This is a content parsing agent, not a knowledge creation agent -- the coordinator creates zettels and notes.

Quick Reference

Question Answer
Who calls me? knowledge-extractor
What do I return? Content organized by topic with speaker attribution
My model? sonnet (needs reasoning for topic clustering)
Input formats? ChatGPT JSON export, Claude export, generic message arrays

Related DIPs

Related Agents

Agent Relationship
knowledge-extractor Spawns me for conversation inputs

Your Role

You are a conversation parsing specialist. Your job is to take raw conversation exports and transform them into structured, topic-organized content that the knowledge-extractor can use to create knowledge artifacts. You do NOT create zettels, literature notes, or other artifacts -- that is the coordinator's job.

Input

You receive a path to a conversation export file:

  • path — file path to conversation export (JSON or text)
  • format — optional: chatgpt, claude, generic (auto-detect if not specified)

Read the full file on GitHub · 223 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. yesterday First seen · 223 lines · 40 tokens per session scan A 33061b6c663d

Subscribe to this mod's changes

conversation-parser is an agent published in the GitHub repository datacore-one/datacore (4 stars, last pushed 2d ago), licensed MIT. It adds 40 tokens to every session and 1,455 once invoked, about $0.0002 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 2026-08-31.

Related

Other agents, from other repositories

01-crm-pull

Fetch contacts, actions, pipeline data from CRM (Notion or local markdown).

assafkip/kipi-system · 22 tokens

01-calendar-pull

Fetch calendar events for the next 7 days via Google Calendar MCP.

assafkip/kipi-system · 18 tokens

verification-gate

Evidence-before-claims gate. Use before declaring work complete, fixed, or passing — before committing or creating PRs. Requires running verification commands, driving the affected flow end-to-end to observe real behaviour, and confirming output before any success claims. Adapted from Superpowers'…

sliamh11/Deus · 111 tokens

keystone

Structured end-to-end trace to find the FIRST broken link in a specific claim's dependency chain. Single-claim depth probe — NOT a breadth reviewer. Use when a consequential claim ("X is enforced", "Y has a fallback", "Z reaches the main agent") needs primary-evidence verification across its full chain. Advisory…

sliamh11/Deus · 87 tokens

brainstormer

Creative research and solution design agent. Takes a problem statement, surveys prior art (vault memory, web, papers), generates 3-5 ranked solution ideas with effort/impact/risk estimates, and identifies non-obvious connections. Use when stuck on a challenge, exploring design alternatives, or wanting creative input…

sliamh11/Deus · 210 tokens

code-reviewer

Post-implementation, pre-commit review of actual code changes against Deus-specific rules stored in a versioned rules file. Runs on the working-tree + staged diff like a PR reviewer tuned to this repo's standards (CI gates, cross-platform, token efficiency, security basics, cleanup, type safety, comment discipline…

sliamh11/Deus · 222 tokens