> ## Documentation Index > Fetch the complete documentation index at: https://docs.modusbrain.com/llms.txt > Use this file to discover all available pages before exploring further. # Lens Packs > View your knowledge through different lenses for specific use cases. # Lens packs (v0.41.2.0) Four bundled schema packs that turn the modusbrain dream cycle into a multi-lens brain. Activate one with `modusbrain config set schema_pack <name>` and the cycle picks up the pack's declared phases on the next `modusbrain dream` run. ## The four packs ``` gbrain-base (shipped v0.38) ▲ │ extends ┌──────────────┼──────────────────────┐ │ │ │ modusbrain-creator modusbrain-investor modusbrain-engineer (atom + concept (deal/thesis/ (learning bridge lifecycle) bet_resolution) for gstack) │ │ │ └──────────────┼───────────────────────┘ │ extends + borrow chain ▼ modusbrain-everything (meta-pack) one brain, three lenses active ``` ### modusbrain-creator Atom + concept content-creator lifecycle. Drives two cycle phases: * `extract_atoms` — per source, Haiku extracts 1-3 atoms from each transcript with the closed 11-value `atom_type` enum (insight, anecdote, quote, framework, statistic, story\_angle, strategy\_angle, strategy, endorsement, critique, collection). Writes `atoms/{YYYY-MM-DD}/{slug}` pages. Budget cap \$0.30/source/run. * `synthesize_concepts` — globally aggregates atoms by frontmatter `concepts:` ref. Tier by count: T1 ≥10, T2 ≥5, T3 ≥2. T1/T2 get Sonnet narratives; T3 falls back to a deterministic stub. Writes `concepts/{slug}` pages. Budget cap \$1.50/run. One calibration domain: `concept_themes` / cluster\_summary / \[concept] — tier histogram + page count, not Brier (concepts don't have binary outcomes to score against). ### modusbrain-investor YC / investor lens. Declares 2 net-new page types on top of gbrain-base's deal/person/company/yc seed: * `thesis` (NEW) — investment thesis with thesis\_text + key\_bets\[] + market\_view + vintage. Files at `investing/theses/{slug}`. Extractable (the LLM mines claims into facts). * `bet_resolution_log` (NEW) — outcome record for a thesis's bet. FK to a take row via take\_id; carries resolved\_outcome + resolved\_at + learned\_pattern. Files at `investing/bets/{YYYY-MM}/{slug}`. No new cycle phases — consumes the existing extract\_facts/propose\_takes/grade\_takes/calibration\_profile loop. Three calibration domains: `deal_success` (scalar\_brier over deal-attached takes), `founder_evaluation` (scalar\_brier over person-attached takes), `market_call` (weighted\_brier over thesis-attached takes; weighted by conviction so high-stakes misses cost more). ### modusbrain-engineer Bridge-only pack. Declares `learning` page type + reuses base `code`. No new cycle phases — the daemon-side `gstack-learnings` IngestionSource (T8) watches `~/.gstack/projects/{repo}/learnings.jsonl` and emits each JSONL line as a `learning` page when this pack is active. Three calibration domains: `architecture_calls` (scalar\_brier), `effort_estimates` (weighted\_brier), `risk_assessment` (scalar\_brier). Speculative ADR/postmortem/refactor\_thesis/tech\_debt types deferred to v0.42+ — they'll ship when a real user authors the first one (D8). ### modusbrain-everything Meta-pack stacking creator + investor + engineer via the v0.38 `extends` + `borrow_from` chain. Single-active-pack constraint preserved — this IS the active pack; the registry walks extends + borrow to materialize the merged view. Activate via `modusbrain config set schema_pack modusbrain-everything` and calibration\_profile produces all 7 domain scorecards in one JSONB. ## Calibration profile widening (T10) Before v0.41.2.0, `calibration_profiles.domain_scorecards` was a `JSON.stringify({})` placeholder. v0.41.2.0 widens it: each declared domain produces a `{n, brier, accuracy, aggregator, page_types, extras}` entry. Four aggregator algorithms (closed enum): * **scalar\_brier** — `AVG(POWER(weight - outcome::int, 2))`. Default for probabilistic predictions. * **weighted\_brier** — Brier weighted by `ABS(weight - 0.5) * 2` (conviction proxy). High-conviction misses cost more. * **count\_based** — simple `SUM(hit) / COUNT(*)` accuracy without Brier. Use when probability isn't natural. * **cluster\_summary** — descriptive rollup (page count + tier histogram). For domains like `concept_themes` where there's no binary outcome. Pack manifests declare domains with `{name, aggregator, page_types}`. Domain names are OPEN (third-party packs can declare new domain labels without a modusbrain release). Aggregator algorithms are CLOSED (safe SQL stays in code, validated at pack-load). ## take\_domain\_assignments table (T1) New JOIN table (migration v94): `take_domain_assignments(take_id BIGINT FK, domain TEXT, pack TEXT, source TEXT, confidence REAL, assigned_at TIMESTAMPTZ, PK(take_id, domain))`. Multi-domain assignment honest — a take about "Sequoia's investment in Anthropic" can land in BOTH `deal_success` AND `market_call` rather than being force-bucketed. ## What this enables for the user * **Atoms + concepts ship in the binary.** Your OpenClaw's parallel atom-pipeline-coordinator + atom-backfill-coordinator + concept- synthesis crons can retire (T12 follow-up). One `modusbrain dream` cron covers everything. * **gstack learnings reach modusbrain.** Engineer-pack-active brains surface every gstack-logged learning as a queryable page within seconds of being written. * **Multi-lens calibration.** Activate modusbrain-everything and see how often you're wrong on deals AND market calls AND architecture AND effort estimates in one `modusbrain calibration --json` call. * **Lossless OpenClaw migration.** The `markdown-greenfield` importer (T7, mode='migration') re-ingests existing OpenClaw pages with permanent slug-keyed idempotency + per-row JSONL audit * the `imported_from` marker so extract\_atoms + synthesize\_concepts don't re-extract already-atomized material. ## v0.41.2.1 follow-ups (filed in plan) * Per-page-type `frontmatter_validators` on PageTypeSchema so the atom\_type enum (currently hardcoded in extract\_atoms.ts) reads from the active pack manifest at runtime per D11. * 3-check quality gate (truism / punchline / entity-page reject) as a multi-pass extract\_atoms refinement. * Embedding-similarity dedup in synthesize\_concepts (currently exact-string concept ref match only). * Voice gate integration for T1 Canon narratives. * op\_checkpoint resumability for cross-cycle continuation in both phases. * Parity-baseline eval gates against your OpenClaw's existing 13K atoms * 11K concepts on a 500-page sample subset.