Agent
Given a retracted or updated belief, traces the justification index for sole-justification dependents and classifies each downstream note by argumentation attack type. Produces an impact map for user review before any rewrites.
Agent
Web researcher for /discovery journeys. Searches iteratively until mechanical convergence detection signals saturation.
Agent
Vault knowledge scout for /discovery journeys. Searches existing Obsidian notes and episodic memory to surface what the user already knows about a topic.
Agent
Socratic lens across knowledge bases. Surfaces tensions, questions absences, and flags thin ice. Never judges: presents what a critical thinker needs to see.
Agent
Batch inbox triage agent. Classifies intention status (intentioned/resolved/limbo), clusters by topic, assesses maturity via promote-gate, routes to correct folders, surfaces top-5 limbo notes for close-or-plan decision, detects counter-arguments, and executes promotions autonomously. Sweeps 1-fleeting/ for archival…
Agent
Extracts atomic insights from any content Claude can read: text, PDFs, images, code, conversations, docs, or any other format.
Agent
Fetches and extracts insights from Linear tickets. Pulls assigned tickets or project-scoped tickets, extracts patterns and project state.
Agent
Maps architectural layers, data flow, key abstractions, and entry points for a repository being ingested. Writes ARCH.md to ingested-repos/ / with file:line citations.
Agent
Maps coding conventions, naming patterns, import organization, testing patterns. Writes CONVENTIONS.md to ingested-repos/ / with file:line citations.
Agent
Maps the problem space, core assumptions, mental model, and anti-goals of a repository. Writes DOMAIN.md to ingested-repos/ / with file:line citations.
Agent
Maps tech stack, dependencies, integrations, and runtime config for a repository being ingested. Writes STACK.md to ingested-repos/ / with file:line citations.
Agent
Captures ephemeral project state (current branch, recent commits, in-flight work, surface-visible concerns) from a repository being ingested. Returns inline JSON to coordinator, writes NO files.
Agent
Scans a repository and extracts architecture, stack, patterns, and project context as insights.
Agent
Merges 4 structured mapper docs + state sidecar JSON into confirmedinsights JSON for the existing route-output pipeline. Read-only; no file writes.
Agent
Captures an external source as a literature note. Fetches content, extracts core ideas in persona voice, finds vault connections and counterpoints, verifies claims, writes to 2-literature/.
Agent
Strengthens a single vault note. Assesses maturity, researches gaps scaled to need, rewrites in persona voice, verifies sources, promotes when ready. Splits multi-idea notes.
Agent
Batch note quality scorer for the Obsidian vault. Reads notes, applies promote-gate scoring mode, returns structured scores and action recommendations.
Agent
Verifies note claims against cited sources. Checks source URLs are reachable, claims are supported, and no references are fabricated. Returns 4-level ordinal confidence per claim (strong/partial/no source/contradicted) with specific issues.
Agent
Persona-voiced note writer for the Obsidian vault. Takes topic, research findings, and optional existing note content: produces atomic notes following capture-rules.md in Hemingway/Musashi/Lao Tzu voice.
Agent
Proposes upstream refinements when a new vault note touches an existing claim. Returns structured JSON for the driver to apply via Write or counter-argument linking.