Skip to main content

Methods

A method is a learned workflow. When an agent finishes a multi-step task, it can save the sequence of tool calls as a YAML body that future tasks reuse. Methods sit alongside Skills and Tools in the same capability index — the agent discovers and loads all three through the same mechanism.

This page is the developer reference: what's in a method, how scoring works, where they're stored, and how capability discovery around methods/tools/skills works.

What's in a method

PropertyDescription
nameDisplay name
descriptionBrief description (used by capability discovery)
triggerTextOptional phrases that activate this method ("deploy to staging", "publish post")
bodyThe YAML workflow — step-by-step tool calls with logic between them
toolsUsed / skillsUsedAuto-extracted from body so loading the method auto-loads its dependencies
tokenCountEstimated cost for context budgeting
versionBumped on every edit

Loading a method automatically loads its referenced tools and skills. So an agent that starts with research skills can pull in a "deploy to staging" method (and the tools that method uses) without you doing anything.

Scoring

Methods are scored using a recency-weighted success rate:

score = successRate × recencyWeight
recencyWeight = 1.0 / (1.0 + daysSinceUsed / 30.0)

Each time a method is used, the system records a MethodEvent (loaded, succeeded, failed) and recalculates the score. High-quality, recently-used methods rank higher in search results — so the workflows that actually work float to the top automatically.

How capabilities are selected

Each agent has a tool mode (in the agent's Capabilities settings). In Auto mode (the default), the model starts each session with a small, fixed always-loaded hot set and expands it on demand from your enabled capabilities. In Manual mode, all enabled capabilities are sent to the model every turn.

Mid-conversation discovery

In Auto mode, the agent expands its kit while a chat is in progress via two always-on tools:

ToolWhat it does
capabilities_discoverSearch enabled methods, tools, and skills in one call; returns ranked IDs like tool/sandbox_exec or skill/plot-data
capabilities_loadLoad specific capabilities by ID into the active session

Loading a method through capabilities_load automatically loads its referenced tools and skills.

Storage

Methods live in ~/.osaurus/methods/methods.sqlite (SQLCipher-encrypted if you've opted in to storage encryption).

Browsing methods

There isn't a dedicated "Methods" tab in the app — methods live alongside skills in the same capability index. To inspect what's been learned:

  • Management → Insights shows when methods were loaded and whether they succeeded or failed
  • The methods database is browsable via SQLite tools if you really need to dig in

Skills, Methods, Tools — the comparison

SkillsMethodsTools
SourceYou author them or import from a marketplaceAgents save them after successful runsBuilt-in plugins, native plugins, MCP providers
ContentMarkdown instructions + reference filesYAML sequences of tool callsCode (Swift, Rust, Python via MCP)
What they doAdd domain knowledge / methodologyReplay a known-good workflowTake action (read files, run commands, call APIs)
Loaded byOn-demand discovery (capabilities_discover / capabilities_load)On-demand discoveryHot set + on-demand discovery; loading a method auto-loads its tools
Token costThe skill's instructions textThe method's YAML bodyJust the tool's spec (description + parameters)

Related:

  • Skills — user-facing skills documentation
  • Tools & Plugins — what tools exist and how they're built
  • Agents — capabilities are scoped per agent