conversation-dump

A conversation-analysis tool for Claude Code or Codex CLI histories. It extracts dialogue and classifies user messages using six academic frameworks for questions and reasoning.

In plain words
What is it for?
Use it to batch-extract sessions, group them by topic, and analyse each user message across cognitive level, question depth, reasoning, assumptions, and conversational purpose.
Why use it?
It turns many past conversations into a structured dataset, making recurring topics, question types, and reasoning patterns easier to examine.

Skill for Claude CodeCodex

Part of the sci-brain plugin — 13 skills shipped together

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 skills/quantumbfs/sci-brain/conversation-dump
Any agent
npx skills add QuantumBFS/sci-brain --skill conversation-dump
Clone the repo
git clone --depth 1 https://github.com/QuantumBFS/sci-brain

Made for: Claude Code, Codex.

Or install sci-brain, the plugin that ships this one along with the rest of its 13 skills.

Per session 71 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,753 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 $0.00071 $0.01753
Opus 5 $0.00036 $0.00877
Sonnet 5 $0.00014 $0.00351
Haiku 4.5 $0.00007 $0.00175

Measured 3d ago against content hash 5e68b84fb1a2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

conversation-dump 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 3d ago.

The scan reads SKILL.md. This mod also ships 2 executable files (extract_dialog.py, parse_md_dialog.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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/conversation-dump/SKILL.md · 154 lines

How it starts

The opening of the file, as written. The whole thing — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Dialog Analysis

Analyze all conversation sessions from a chosen source (Claude Code or Codex CLI) in three phases: batch extraction, topic classification, and deep 6-dimension analysis.

Phase 1 — Extract

Ask the user to choose a source: claude or codex.

List and extract ALL sessions in batch using the Python script:

python skills/conversation-dump/extract_dialog.py list --source claude --project all
python skills/conversation-dump/extract_dialog.py list --source codex

Extract every listed session and save the JSON output to a staging directory:

mkdir -p docs/dialog/<source>/extracted
python skills/conversation-dump/extract_dialog.py extract --source <source> --session <id> > docs/dialog/<source>/extracted/<session-id>.json

Run extractions in parallel (batch shell commands). Skip sessions that yield 0 user turns after filtering.

Phase 2 — Classify by Topic

Dispatch fast available agents in parallel to classify each extracted session by conversation topic. Each agent receives a batch of ~20 extracted JSON files and returns a topic label for each.

Topic taxonomy (closed set):

Slug Description
skill-design Designing or refining skill definitions
brainstorming Research ideation, /brainstorm-ideas sessions
code-review Reviewing code or PRs
debugging Fixing bugs, diagnosing failures
documentation Writing or editing docs, READMEs
ci-cd CI/CD pipelines, GitHub Actions, deployment
refactoring Restructuring existing code
research Literature search, paper discussion
plugin-management Plugin install, config, marketplace
slide-creation Presentations, Typst/LaTeX slides
paper-review Reviewing or analyzing academic papers
testing Writing or running tests
configuration Settings, environment, permissions
project-setup Scaffolding, init, dependencies
automated No real human messages (system/skill invocations only)
other Does not fit any above — agent must propose a slug

Read the full file on GitHub · 154 lines

Files

What ships with it

3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 3d ago First seen · 154 lines · 71 tokens per session scan A 5e68b84fb1a2

Subscribe to this mod's changes

conversation-dump is a skill published in the GitHub repository QuantumBFS/sci-brain (81 stars, last pushed 6d ago), licensed MIT. It adds 71 tokens to every session and 1,753 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

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens