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 skills add QuantumBFS/sci-brain --skill dump-chat-historygit clone --depth 1 https://github.com/QuantumBFS/sci-brainWrote 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.
[](https://agentmods.dev/skills/quantumbfs/sci-brain/dump-chat-history)<a href="https://agentmods.dev/skills/quantumbfs/sci-brain/dump-chat-history"><img src="https://agentmods.dev/badge/skills/quantumbfs/sci-brain/dump-chat-history/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.
<a href="https://agentmods.dev/skills/quantumbfs/sci-brain/dump-chat-history"><img src="https://agentmods.dev/badge/skills/quantumbfs/sci-brain/dump-chat-history.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00034 | $0.01771 |
| Opus 5.5 | $0.00014 | $0.00708 |
| Sonnet 5.5 | $0.00007 | $0.00354 |
| Haiku 4.5 | $0.00003 | $0.00177 |
Grade A, and why
dump-chat-history 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 29d 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 — 165 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Installed resources
Own history acquisition, source reconciliation, and faithful transcript export.
how-to-analyze-dialog owns research-topic classification and six-dimension
prompt analysis; create-advisor owns advisor profiles. A field note may contain
brief evidence-backed annotations, but exporting alone does not request either
analysis workflow.
Resolve this loaded SKILL.md to its real path before finding helpers/,
references/, or assets/; copied/symlinked skills need not be siblings.
Set DUMP_HISTORY_DIR to that absolute skill directory, keeping the working
directory at the user's project. Locate optional downstream skills by public name.
1. Select sources and time range first
Before reading conversation contents, establish which source(s) and from when. Honor selections already provided, including in a calling skill; ask only for missing information. Allow multiple harnesses. Present the full source menu in the first selection, not only whichever clients happen to be installed:
- Codex (CLI/app)
- Claude Code
- pi agent
- OpenCode
- DeepSeek harness/client
- Kimi Code
- Gemini CLI
- GitHub Copilot CLI
- Cursor
- Windsurf
- Aider
- Cline / Roo Code
- Another harness — user enters its name
- Supplied JSON, JSONL, Markdown, or application export
Ask for a start date or relative range, such as “since 1 September”, “past week”,
or “all available history”. Include the end date (default: now) and timezone
(current user timezone when known) in the resolved scope. For a date-only start,
use local midnight; for “past week”, subtract seven days from a captured current
time. Record exact boundaries and use [start, end). If timezone is unknown,
ask before filtering. Do not silently assume all history.
A compact first question can ask both: “Which harnesses, and from when? [source menu]. You can select several or enter another name; for example, Codex + Claude Code, past week.” Use a real free-text field for another harness, not an “etc” option. If the UI limits option counts, show the named menu in the question and accept names in free text.
What ships with it
6 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.
- 29d ago Changed · +4 lines 4afe7590983f
- 1mo ago First seen · 161 lines · 34 tokens per session scan A 764278d8aebd
dump-chat-history is a skill published in the GitHub repository QuantumBFS/sci-brain (101 stars, last pushed 23d ago), licensed MIT. It adds 34 tokens to every session and 1,771 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 2026-09-11.
Other skills, from other repositories
foundry-hosted-agent-validation
Step-by-step process for validating a Python Foundry hosted agent sample (under python/samples/04-hosting/foundry-hosted-agents/) end to end — running it locally (native runtime and azd ai agent run) and after deploying it to an Azure AI Foundry project with azd. Use this when asked to validate a hosted agent sample.
skill-doc-delivery
Convert markdown to DOCX, PPTX, XLSX, PDF office documents — use when you need exportable deliverables.
meta-web-to-pdf-briefing
Render a topic into a distributable PDF briefing in three steps: web search → bullet summary → styled PDF. Trigger when the user asks for a PDF briefing on a single topic.
chat-complex-documents
Chat with and search your complex documents — ask questions, extract tables and fields, and get answers grounded in the source. Connects the hosted Unstructured Transform MCP server to parse, structure, and enrich PDFs, Word/Excel/PowerPoint, images, scanned files, emails, and 60+ other formats into clean, AI-ready…
pkf-writing
Author, update, convert, validate, persist, and render PKF (.pkf) content through message-inline, Library Asset, or Memory Page carriers. Use for structured reports, knowledge pages, delivery cards, or any .pkf body. NOT for recall, memory-graph placement, or curation decisions — those belong to the memory skill.
paper-reader
A reading assistant for computer-vision and deep-learning research papers. It can work with PDF files, arXiv papers, and papers stored in Zotero, a reference-management app.