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/incarnatenpx skills add QuantumBFS/sci-brain --skill incarnategit 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 | $0.00052 | $0.02954 |
| Opus 5 | $0.00026 | $0.01477 |
| Sonnet 5 | $0.00010 | $0.00591 |
| Haiku 4.5 | $0.00005 | $0.00295 |
Grade A, and why
incarnate 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 2d 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 — 255 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Advisor Profile Generation
Onboard a contributor and create a named advisor profile. The profile captures how a real person thinks — their cognitive style, attention patterns, reasoning strengths, and conversation dynamics — so the brainstorm-ideas skill can launch them as a subagent collaborator rather than a thin inline persona.
Choose the mode
- Create an advisor: start at Step 1 and run the complete workflow.
- Update an advisor from new conversations: read the existing
advisors/<slug>/profile.md, preserve its background, then start at Step 2 with the new JSONL or Markdown sources. - Import Markdown dialogs: ask for the file paths and target advisor, then use the Markdown path in Step 2. For a new advisor, collect the Step 1 background first.
- Analyze thinking patterns only: run Conversation Pattern Extraction and stop after writing
thinking-pattern.mdandmaster-thinking.md; do not synthesize an advisor profile unless the user asks.
Step 1 — Personal Profile
Ask the contributor to provide their academic/professional background:
- (a) Tell me yourself (field, experience, what you've worked on)
- (b) Zotero library — follow the
know-me-betterskill instructions (skills/know-me-better/SKILL.md) to index publications - (c) Google Scholar profile — follow the
know-me-betterskill instructions to index publications
From the response, extract:
- Name (ask if not provided)
- Field and subfields
- Key research themes
- Technical skills
- Notable contributions
- Publication sources if available (homepage, Google Scholar, ORCID, DBLP, arXiv author page)
- Voice preference if available (spoken language, accent, or preferred
edge-ttsvoice)
Hold this information for Step 4.
Advisor KB. Each advisor gets a private knowledge base at advisors/<slug>/.knowledge/ (shape identical to the project KB: INDEX.md, NOTES.md, .raw/, .figures/, rendered <id>_<slug>.md files). The advisor's BibTeX namespace lives at advisors/<slug>/.knowledge/references.bib (i.e. $KB/references.bib for the resolved advisor KB). When know-me-better or download-ref is invoked from this skill, resolve the advisor KB path via python3 skills/download-ref/helpers/resolve_kb.py --advisor <slug> and pass it as --kb "$KB" so writes land in the advisor KB rather than the project KB. (Users who set $SCIBRAIN_KB_DIRNAME get the right directory name automatically.)
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.
- 2d ago First seen · 255 lines · 52 tokens per session scan A 1202b7510208
incarnate is a skill published in the GitHub repository QuantumBFS/sci-brain (81 stars, last pushed 6d ago), licensed MIT. It adds 52 tokens to every session and 2,954 once invoked, about $0.0003 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.
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…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.