agenticonsult logoagent i /consultDocs
Agentic infrastructureAgents

Agents

The agent roster in depth — every family of specialists, what dispatches each one, and how you direct them.

An agent is a Markdown file. The roster ships in .claude/agents/ under your install root — 48 definition files, each a readable job description: who the specialist is, when to use it, which tools it may touch, which model it runs on, and the full working method in plain prose. There is no compiled agent and no hidden registry. The file is the agent, and editing it changes behavior on the very next run.

This page documents the roster by family — what each group of specialists does, when the system reaches for it, and how you interact with it. The flat one-row-per-agent table lives in Catalogs; the ideas behind delegation live in Missions, operations & the fleet.

What an agent definition is

Every file follows the same contract — YAML frontmatter over a prose body:

FieldWhat it does
nameThe dispatch name — how sessions and daemons refer to the agent
descriptionThe when-to-use statement. This is what a dispatching session matches against when picking a specialist
toolsAn exclusive allowlist. Listing tools restricts the agent to exactly those; omitting the line inherits everything. An agent's entire tool reach is visible in one line of its file
modelA per-agent cost/quality dial — opus for judgment-heavy work, sonnet for mechanical throughput, haiku for the cheapest checks. Change one word to retune
skillsOptional skills the agent loads for its craft
memoryOptional — grants the agent its own persistent memory file across runs

The body below the frontmatter is the agent's method: its workflow, its output contract, its rules. Read any file in the Agents view to see exactly how a specialist thinks — that transparency is deliberate, and it extends to editing: changes are live on the next spawn, with nothing to restart.

A few roster files carry only a comment block instead of full frontmatter. Those are pipeline-only agents: they are never dispatched by name from a session — the automation daemon spawns them directly and they read their own definition as instructions. You will meet them in the intelligence desk and pipeline families below.

The three ways an agent runs

Not every agent runs the same way, and the run surface shapes how you interact with it:

SurfaceWhat it isYou see it as
Dispatched specialistA session hands one bounded job to a roster agent; it works in an isolated context, returns a summary, and endsThe dispatching session reports back; output files land in your workspace
Fleet sessionA persistent, full-capability agent session in a terminal pane, grounded with a role file and a missionA live pane in the Terminals view — watch it, type into it, pause it
Scheduled or triggered runThe automation daemon spawns a fresh headless session that executes a routine, often as one of these agentsA run entry with a log in the Routines view

The rule of thumb: bounded and parallel work goes to dispatched specialists, recurring work goes to routines, and long coordinated workstreams become a mission fleet. The routines concept page covers choosing between them.

The mission fleet pair

Two definitions are not dispatched specialists at all — they are role files that ground the fleet:

AgentRole
mission-commanderRuns one mission end to end: reads the dossier, decomposes it into operations, assigns workers, evaluates results against the success conditions, and completes the mission through the gate
mission-workerExecutes exactly one operation: reads its brief from disk, works it with full platform capabilities, writes durable output into the operation folder, reports done or blocked

When you dispatch a mission from the Missions Board, the platform stands up one terminal workspace with a commander pane and worker panes; each pane is a full agent session with the matching role file injected as its operating posture. The commander holds the whole picture; each worker sees only its slice. You interact by watching the panes live, typing into any of them, or pausing all agent terminal control with one switch — the fleet is deliberately visible. Full narrative: Missions, operations & the fleet.

Research & audit

The judgment-heavy specialists. You (or another agent) dispatch them with a question or a target; they return a report — usually a dated Markdown file in your documents tree, tagged with the agent's two-letter author code in the filename.

AgentModelWhat it does
deep-researcherOpusMulti-phase research on any topic — multi-source, cited, produces a structured report file
quick-researcherSonnetFocused lightweight research — a handful of sources, returns findings as text rather than a report
deepdive-authorOpusA verbose, primary-source deep-dive on a feature, subsystem, or codebase, written for a named downstream consumer — the constructive counterpart to an audit
feature-auditorOpusA four-phase production-readiness and correctness audit of any feature — exhaustive reading, workflow tracing, issue identification
critique-validatorOpusAdversarial critique of any agent output — plans, reports, decisions — with structured verdicts built to resist tell-you-what-you-want answers
professor-geminiOpusDomain expert for Google Cloud and Gemini integrations — API verification, migration advice, curated documentation

When the system dispatches them: a session facing a research-shaped or audit-shaped task matches it against these descriptions and fans work out — several researchers can run in parallel on independent questions. When you dispatch them: ask for the audit or the research in any session; the reports land on disk where you (and later sessions) can read them.

Engineering

AgentModelWhat it does
feature-developerSonnetFull-stack implementation — routes, services, components, stores, migrations — following the existing patterns of whatever codebase it works in
refactorerSonnetBehavior-preserving cleanup: deduplication, better abstractions, pattern alignment
dependency-checkerHaikuOutdated packages, known vulnerabilities, license compliance — read-only by design

These are the workhorses for parallel bounded coding jobs: a session splits a build into scoped pieces and dispatches one developer per piece. The auditor and critique agents above pair naturally as the review step.

Knowledge, context & memory

The specialists that maintain the platform's own knowledge layers:

AgentModelWhat it does
context-architectOpusQueries every memory and knowledge layer for a task, then composes a context artifact — the grounding package a new agent session launches with
kg-ingesterSonnetReads documents and extracts entities and relationships into the knowledge graph using its own reasoning — no external extraction service, no per-document API cost
doc-organizerSonnetManages the document lifecycle — files completed reports into the right folders, enforces naming, archives stale material

You rarely dispatch these directly. The graph's Enrich action dispatches the ingester; housekeeping routines dispatch the organizer; the context architect is the one to reach for before a large piece of work, and its output feeds context artifacts.

The products pipeline chain

Ten specialists that together turn a pile of source material into a finished two-part knowledge product. Each owns one stage; the Products view drives dispatch and you approve between stages:

product-sighter (survey the sources) → product-composer (propose an outline) → product-research-scout + product-researcher (plan, then extract section knowledge) → product-consolidator (merge research notes) → product-auditor (cross-section overview and audit) → product-scope-refiner (transform notes into near-final sections) → product-section-finalizer (final polish) → product-human-author (the human-facing manual) — with product-illustrator composing the cover.

One earlier-generation file (product-scout) remains on disk for reference but is no longer dispatched. The full chain, its handoff artifacts, and where your approvals sit are covered in Agent pipelines.

The video pipelines

Two three-agent chains — one per rendering engine — plus a clip-preparation specialist:

AgentPipelineStage
video-brief-authorRemotionEnriches your freeform brief with creative direction — metaphor, color arc, key moments
video-script-authorRemotionWrites the scene-by-scene production script and picks compositions
video-composerRemotionProduces the machine-readable render proposal plus a readable walkthrough for your review
hyperframes-brief-authorHyperFramesRewrites the brief into a denser, reference-aware version
hyperframes-plannerHyperFramesAuthors the storyboard — per-beat direction, exact block picks, install list
hyperframes-html-authorHyperFramesWrites all composition HTML, installs the planned blocks, lints and fixes before finishing
footage-editorEitherPrepares one raw clip per instruction — transcribe, cut fillers and silence, grade, trim — producing a clean asset for either pipeline

Each trio deliberately narrows knowledge per stage: the brief authors know capability categories, the middle agents know the catalog by name, and only the final agent holds the deep authoring surface. You review between every stage in the Video view, and nothing renders until you dispatch it. Stage order and handoffs: Agent pipelines.

The intelligence desk

The writers and analysts behind the news pipeline. Most are pipeline-only agents — the automation daemon dispatches them on schedule or on your trigger, never by name from a chat session:

AgentWhat it does
observer-agentDigests batches of harvested news items into observer reports — summarize, categorize, score
news-scoutProposes briefing-worthy story clusters from the report pool; one writer run is spawned per cluster
news-writerWrites one source-grounded 200–400 word briefing per cluster, with impact metadata
breaking-writerExtracts short time-sensitive ticker items from fresh reports, deduplicated against the last 72 hours
report-scout + report-writerThe deep-dive tier — the scout proposes report candidates, the writer produces typed long-form intelligence reports
roundup-writerOne weekly multi-topic roundup from the week's material
newsletter-writerCurates a bilingual email digest — always as a draft; sending is a separate, explicit human action
news-translatorProduces native-quality translations of published articles into your configured locales
news-illustratorComposes editorial hero-image prompts for fresh articles; the local image daemon renders them
yt-video-analyzerDeep 8-section analysis of a harvested video from its transcript, keyframes, and metadata

You direct this family through the intelligence views: configure sources, enable the routines that schedule the writers, review what they produce, and approve anything outbound. The fan-out shape — scouts propose, the daemon validates and spawns one clean-context writer per item — is explained in Agent pipelines.

Support

AgentModelWhat it does
support-emailSonnetWorks the support inbox queue — reads new mail, classifies it, pulls context from the knowledge base, drafts a reply, and waits for your approval before anything sends

The approval gate is architectural: every outbound email requires a human decision, no matter how routine the draft looks. That is the same unconditional rule the whole operator model enforces.

Working with the roster

  • Inspect and edit in the Agents view. Every definition opens as an editable file grouped by category. What you read is exactly what the agent executes.
  • Clone before you write from scratch. The Create and Clone dialogs prefill frontmatter — name, model, description, a tool picker grouped by server, a skills selector — from any existing agent. The shipped roster is a set of proven templates, not a fixed menu.
  • Or just drop a file. A new .md in .claude/agents/ with valid frontmatter is a new agent. No registration, no build, no restart.
  • Curate tools deliberately. A narrow tools: line makes an agent safer, cheaper, and more predictable. Give an agent only what its job needs.
  • Match the model to the stakes. Judgment work earns opus; mechanical volume runs on sonnet or haiku. It is a one-word edit per agent.
  • Know the author codes. Report-producing agents sign their output files with a two-letter code in the filename (for example _dr_ for the deep researcher), so you can always tell which specialist wrote what you are reading.

Where to go next

On this page