Skip to content

Agent Presets ​

A preset is a ready-made agent: a system prompt, sensible settings, and the skills it needs. Pick one with preset: and you only choose the model.

halo
agent Sorter   [openai/gpt-4o-mini, preset: Classifier]
  system "Labels: billing, bug, feature_request, other."

agent Reviewer [anthropic/claude-sonnet-4-5, preset: CodeReviewer]
agent Gate     [anthropic/claude-haiku-4-5, preset: Judge]

pipeline Route(email: String) -> Result:
  email
    |> Sorter.classify() as kind
    |? (context.data.kind.confidence >= 0.7)
PresetDoesSettingsSkillsAnswers
SummarizerShort, faithful summaries that keep names, numbers and decisionstemp: 0.2text
ClassifierPicks exactly one label from the ones you givetemp: 0{ label, confidence, reason }
ExtractorPulls the fields you ask for out of text, null when absenttemp: 0data-extractionthe requested fields
JudgeGrades work against your criteriatemp: 0{ pass, score, reasons, fixes }
ResearcherSearches and reads with its tools, answers with cited sourcestemp: 0.3, max_steps: 20, tools: autoweb-researchtext with sources
WriterClear prose for the audience you nametemp: 0.6text
EditorTightens and corrects text, keeping meaning and voicetemp: 0.2text
PlannerBreaks a goal into ordered, checkable stepstemp: 0.2{ goal, assumptions, steps: [{ id, task, depends_on, done_when }], risks }
CoderChanges code with its tools in small, tested stepstemp: 0, max_steps: 40, tools: autowrite-testsa summary of what it changed
CodeReviewerReviews a diff for bugs and security problemstemp: 0code-review{ verdict, summary, findings }
TranslatorTranslates into to:, keeping formatting and placeholderstemp: 0.2text
TriagerTriages bug reports: kind, severity, duplicate, what's missingtemp: 0bug-triage{ kind, severity, reproducible, duplicate_of, area, labels, missing, summary, reply }
EvolverRewrites a Halo pipeline to do better on its criteria, inside its fence (used by halo evolve)temp: 0.8, max_tokens: 8000Rationale: line and a ```halo block

halo agents prints this list. Preset names are case-insensitive, and halo validate reports one that doesn't exist.

Changing a preset ​

Anything you write on the agent wins:

  • Settings in the brackets replace the preset's: [openai/gpt-4o, preset: Writer, temp: 0.9].
  • system is added after the preset's prompt, so use it for what's specific to you: the labels to choose from, the criteria to judge by, your audience, your codebase's conventions.
  • skills: adds to the preset's skills: [..., preset: CodeReviewer, skills: "house-style"] (see Skills).
  • equips and requires work as on any agent. Researcher and Coder use tools: auto, so they can call every tool they equip; give them tools and a tool policy to fence them in:
halo
policy ReadOnly : AllowEffects(read)

tool Web    : WebSearch()
tool Reader : Browser(maxChars: 8000)
tool Repo   : Git(".")

agent Scout [anthropic/claude-sonnet-4-5, preset: Researcher]
  equips Web, Reader
  requires ReadOnly

agent Reviewer [anthropic/claude-sonnet-4-5, preset: CodeReviewer, tools: auto]
  equips Repo

Coder is best given a computer to work on: [..., preset: Coder, sandbox: "e2b"] gives it a fresh cloud sandbox for each run, and sandbox: "docker" a container on this machine (see Remote Computers).

Presets that answer JSON tell the model the exact fields, and Halo parses JSON answers, so gates can read them directly: |? (context.data.verdict.pass == true). To make a pipeline fail when the shape is wrong, give it a schema return type.

curl -fsSL https://halolang.com/install.sh | sh