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.
npx agentmods add skills/quantumbfs/sci-brain/conversation-dumpnpx skills add QuantumBFS/sci-brain --skill conversation-dumpgit clone --depth 1 https://github.com/QuantumBFS/sci-brainWhat 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.
| Model | Per session | Once 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 |
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.
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.
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 |
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.
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.
- 3d ago First seen · 154 lines · 71 tokens per session scan A 5e68b84fb1a2
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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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.
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.
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.
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.
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…