Maintains a persistent, folder-based log of all agentic-os experiment runs. Each run writes one dated file to context/experiment-log/ and updates index.md.
Updates model catalogs and cheapest-model references for all CLI backends (copilot, agy, claude, codex, llama).
Reviews a completed os-eval-runner lab run and backports approved changes to master plugin sources. Trigger with "backport the eval results", "review the lab run", "apply eval…
Trigger with "mine plugins", "analyze plugin collection", "run the full analysis pipeline", "inventory and analyze all plugins", "mine patterns from this directory", or when you…
Trigger with "run self-audit", "test the analyzer", "regression test the plugin analyzer", "audit the agent-scaffolders", or "verify the analyzer works correctly".
Verifies that os-architect actually causes evolution — not just words. Dispatches os-architect in single-shot simulation mode for a given test scenario, then checks for real…
Trigger with "mine this skill", "analyze this skill", "run targeted skill analysis", "extract patterns from this skill", or when you want focused analysis on a single Agent Skill…
Trigger with "evaluate autoresearch fit", "score this skill for karpathy loop", "is this a good autoresearch candidate", "assess autoresearch viability for", "which skills are…
Initializes and orients the agent session using the Protocol 128 Bootloader sequence. Designed as a Dual-Mode Meta-Skill (Bootstrap vs Iteration phase).
Pulls real-time prices for all portfolio positions. Uses TradingView Desktop if running (port 9222), falls back to yfinance automatically per ticker.
Aggregates full monorepo bundle with structured segmentation for deep reasoning audits.
Exports sealed Obsidian vault notes into soul_traces.jsonl format for HuggingFace persistence. Implements snapshot isolation, git pre-flight checks, and consumes the…
Project Sanctuary-specific memory configuration. Maps the generic memory-management tiered system to Sanctuary's actual file paths, storage backends (RLM, Vector DB, Obsidian,…
Use when starting any conversation - establishes how to find and follow the business exploration workflow.
SME-facing front-door skill for Agentic OS ecosystem evolution. Invokes the os-architect interview flow: classifies intent, audits existing capabilities, proposes evolution path…
Change the active TradingView chart symbol. Clicks the symbol button in the chart header, types the ticker, and confirms with Enter.
Generates heavily dimensioned, technical orthographic blueprints intended strictly for carpenters and fabricators.
JSON Hygiene Agent. Detects duplicate keys in JSON configuration files that might be silently ignored by standard parsers. Auto-invoked for JSON audits or manifest validation.
Cancel a Working or Inactive order in TradingView via CDP (clicks the × button on the order row), then marks it cancelled in the Trade Log.
Core markdown syntax skill for Obsidian. Enforces strict parsing and authoring of Obsidian proprietary syntax (Wikilinks, Blocks, Headings, Aliases, Embeds, Callouts).
Master controller for agent session orchestration. Delegated to when starting a session (bootloader orientation), managing workflow routing (Orchestrator, Spec-Kitty), and ending…
Safely removes all agent lock files from the context/.locks/ directory to resolve deadlocks caused by crashed agents leaving stale locks behind.
(Industry standard: Sequential Agent / Agent as a Tool) Primary Use Case: Delegating a well-defined task to a worker agent, verifying its execution, and repeating if necessary.
Trigger: "set up agentic OS", "initialize agent harness", "init my project for AI agents", "where do I put CLAUDE.md", "create my agent environment", "set up persistent memory".
Semantic search agent for code and documentation retrieval using ChromaDB's Parent-Child architecture. Use when you need concept-based search across the repository.
Autonomous end-to-end stock intake & onboarding engine. Takes any stock ticker (held, watchlisted, or completely new), pulls live financials, queries TradingView CDP Data Window…
Audit Vector DB coverage -- compares the live filesystem manifest against the ChromaDB index to identify coverage gaps.
Distills uncached files into the Recursive Language Model(RLM) Summary cache Ledger. You (the agent) ARE the distillation engine.
Determines joinery type per connection based on structural model bounds and user preferences. Explains load transfer behavior and outputs joinery maps.
Adversarial red-team reviewer for Technical Analysis theses. Acts as a Senior Risk Manager and Skeptical Proprietary Trader who challenges TA logic, validates price levels against…
Fetches, analyzes, and lists active TradingView price alerts, saving the snapshot to the backend data folder for offline caching and verification.
Evaluates and improves the exploration-cycle skills, prompts, routing, and artifact quality using baseline-first, one-hypothesis iteration loops with keep-discard decisions and…
Generates a live Grok/X.com prompt from the current target-portfolio.json, receives Grok's structured response, gates each recommendation against DCF and the 8 hard gates, then…
Display kanban board status showing work package progress across lanes (planned/doing/for_review/done).
Presents layout options to the SME in plain language before any prototype construction begins. Invoked after the Discovery Plan is approved to confirm visual structure and…
Semantic link traversal for Obsidian Vaults. Builds an in-memory graph index from wikilinks and provides instant forward-link, backlink, and multi-degree connection queries.
Design and scaffold a Claude Code sub-agent
Derives, groups, and refines user stories from exploration work, prototype behavior, and business context, with prioritization for the first implementation slice.
Captures a TradingView chart screenshot and performs visual technical analysis. Reads the live chart image (with whatever indicators the user has configured) and produces…
A package builder skill that compiles specs/ documents into standard spec-kits and scaffolds the clean target codebase sandbox.
Combined Spec-Kitty agent: Synchronization engine + Spec-Driven Development workflow. Auto-invoked for feature lifecycle (Specify → Plan → Tasks → Implement → Review → Merge) and…
Interactive RLM cache initialization. Use when: setting up a new project's semantic cache for the first time, or adding a new cache profile.
Audits, synchronizes, and maintains the health of the plugin ecosystem. Handles structural compliance checks against Open Standards, agent environment sync (install + cle — from…
Pattern 5: Concurrent Event-Driven Multi-Agent Loop. Coordinates multiple Claude sessions as OS threads sharing a common event bus and memory address space.
Developer machine tool for replicating plugin source code between local project repositories. Use when you want to push plugin updates from agent-plugins-skills to a cons — from…
Captures a chart screenshot for a ticker in TradingView Desktop. Switches the chart to the requested ticker, takes a screenshot, and saves it to…
Trigger with "show me the improvement chart", "how are we improving", "progress report", "graph the eval scores", "show cycle of improvement", "what's the trend", "are we getting…
Translate .mmd diagram files into PNG images with configurable resolution (retina/HQ/scale), supporting rasterization (raster, rasterize, rasterization).
Copilot CLI sub-agent system for persona-based analysis. Use when piping large contexts to GitHub Copilot models for security audits, architecture reviews, QA analysis, or any…
Sync portfolio.json from TradingView's live broker panel (all accounts: TFSA, RRSP, Cash) via CDP. Scrapes positions and balances, shows a diff vs the current portfolio.json (new…
SME-facing orchestrator for the Business Exploration Loop. Supports 4 session types (greenfield, brownfield, discovery-only, spike) with adaptive phase selection.
Scaffold an advanced stateful agent skill with L4 patterns
Converts an input document (.txt, .md, .pdf, .docx) into a structured RSVP token stream with ORP alignment and configurable WPM.
Removes stale and orphaned entries from the RLM Summary Ledger. Use after files are deleted, renamed, or moved to keep the ledger in sync with the filesystem.
Save the current Pine Script in the editor to TradingView's personal library. Handles the "Save as" naming dialog on first save.
Agent skill for safe, dry-run-first, deduplicated, root-cause-consolidated, evidence-validated, and secret-redacted logging of repository execution friction into GitHub Issues.
Draws and annotates horizontal level lines, entry/exit price zones, and text tags directly onto the active TradingView Desktop chart via CDP.
Progressively migrates legacy prototype routes and features to a clean architecture layer slice-by-slice, verifying them against characterization tests, running purity/drift…
Automatically updates the plugin/skill/agent counts in README.md based on the current plugins/ directory.
Challenge and stress-test AI-generated investment thesis valuations that are overly anchored on historical financials.