Agent
Escalation-lane fetcher that drives the user's REAL Chrome browser (via Claude-in-Chrome) for sources headless crawling cannot reach: login-gated pages, bot-walled sites, interactive/infinite-scroll pages, viewer-rendered PDFs, and Google Scholar searches. Drains the hyperresearch escalation queue serially — one item…
Agent
Step 14.5 of the hyperresearch V8 pipeline. Verifies that each sampled citation actually supports its sentence by reading the cited note's body. Receives batches of (sentence, noteid) pairs the mechanical triage could not auto-pass; returns per-pair verdicts (supported / partially-supported / unsupported /…
Agent
Use this agent in Layer 5 of the hyperresearch deep research pipeline. Reads the Layer 4 draft and returns a findings list of places where the draft skates over technical substance that the vault's interim notes could actually support. Spawn ONCE per draft, parallel with dialectic-critic and width-critic.
Agent
Use this agent in Layer 3 of the hyperresearch deep research pipeline. Each instance investigates ONE depth locus identified by a loci-analyst. The agent reads existing vault sources relevant to the locus, fetches new sources as needed (via the hyperresearch-fetcher subagent), and writes ONE interim report note…
Agent
Use this agent in Layer 5 of the hyperresearch deep research pipeline. Reads the Layer 4 draft and returns a findings list of places where the draft ignores, hedges, or straw-mans counter-evidence. Adversarial reading is real reasoning. Spawn ONCE per draft, in parallel with depth-critic and width-critic.
Agent
Use this agent in Layer 5 of the hyperresearch deep research pipeline. Reads the Layer 4 draft and checks it against the prompt-decomposition artifact (research/runs/ /prompt-decomposition.json) produced in Layer 0. Emits findings when atomic items from the prompt are missing, under-covered, out-of-order, or delivered…
Agent
Use this agent in Layer 2 of the hyperresearch deep research pipeline. Reads the width corpus (the sources fetched during the Layer 1 sweep) and identifies 1—8 "depth loci" — specific questions where deeper investigation would meaningfully improve the final report. Spawn 2 of these in parallel; the orchestrator…
Agent
Step 16 agent. Reads the polished final report and writes a JSON file of readability RECOMMENDATIONS (not edits) for the orchestrator to selectively apply. Each recommendation includes the existing text (anchor), the suggested replacement, severity, rationale, and category (merge-paragraphs / break-paragraph /…
Agent
Research fetcher with primary-source-chasing agency. Fetches assigned URLs, reads and summarizes content, extracts structured claims, then follows citation chains and references to discover and fetch primary sources the secondary sources cite. Needs solid comprehension and judgment. Spawn multiple in parallel for bulk…
Agent
Use this agent in Layer 5 of the hyperresearch deep research pipeline. Reads the Layer 4 draft and returns a findings list of topics the width corpus supports but the draft doesn't cover. Spawn ONCE per draft, parallel with dialectic-critic and depth-critic.
Skill Claude CodeCodex
Install Knack on the user's machine. Load this skill when the user asks to install Knack, set up Knack, get started with Knack, or expresses interest in managing AI skills with version control. Handles macOS, Linux, and Windows.
Skill Claude CodeCodex
Conduct the Knack 6-phase interview with a user to author a new skill. Load this skill when the user wants to teach you a recurring task they do and have it become a reusable Knack skill (e.g. "use knack to capture how I triage support tickets").
Skill Claude CodeCodex
Turn a markdown summary/report into a pop-up RSVP speed-reader the user can consume at 500+ WPM. Use when the user asks for a report, summary, digest, or research writeup they want to "speedread", or says things like "make me a report and load it into the reader". Writes the report as markdown, injects it into a…
Instructions file
Instructions for jordan-gibbs/llm-kasten, covering kasten, project structure, commands, architecture and key conventions.