Table of Contents

Agents, tools and skills

Last updated:

Oscova Agents separates an agent's identity from the actions and instructions it can use. This keeps a specialist focused and makes its access easier to review.

Writing/Brand Editor settings with its name, description, instruction controls, and default model provider.

Agents define the working identity

An agent combines its name, instructions, model choice, selected tools, selected skills, memory behavior, task-list behavior, local-only policy and file grants. Oscova Agents creates a main agent during onboarding, and you can add custom agents for focused jobs.

  • Agents can be exposed as tools so another agent can delegate work to them.
  • Admins and moderators can share agents with other users while keeping each user's personal context separate.
  • Saving an agent updates later runs. A response already in progress keeps the configuration it started with.

Tools perform actions

Tools are callable actions such as reading a file, searching a service or running a command. They may come from built-in toolsets, plugins, MCP servers or another agent exposed as a tool.

Note

MCP means Model Context Protocol, a standard way for another program or service to expose tools.

An agent sees a tool only when all relevant controls allow it:

  1. The tool exists and is selected for the agent or task run scope.
  2. Offline or local-only policy permits its effective network scope.
  3. The agent's approval policy does not deny it.
  4. Tool discovery exposes it immediately, through a pin or after a search.
  5. Runtime approval, call limits, hooks and input validation permit the call.
  • Selected tools remain subject to approval policy, folder permissions and Offline mode. An auto-approve setting cannot bypass an offline block, denial, call limit or file-access boundary.
  • With tool discovery enabled, selected pinned tools are visible immediately. Other selected tools stay out of the initial prompt until the agent finds them through tool search. Denied or offline-blocked tools are not returned by that search.
  • In web chat, approval-required calls from a delegated agent return to the parent chat for your decision and identify the executing agent. Where no delegated approval channel is available, those tools are omitted.
  • Encryption of stored conversations does not add a separate agent category.

Use Settings > Agents & AI > Tools to inspect qualified names, effective network classifications, overrides and 24-hour call limits. Select tools and set agent-specific approval behavior in Main Agent, Agents or a task run scope.

Encrypted file tools

Encrypted file tools are a separate encrypted-file surface over ordinary allowed workspace paths. Their filenames must end in .enc, preserving the original extension before it, such as notes.md.enc. Workspace file tools and shell commands see ciphertext. After the Vault Password gate is unlocked, the Files editor decrypts authenticated encrypted text and encrypts it again on save.

Skills provide focused guidance

Skills are imported packages containing instructions and optional resources or scripts. An agent sees only the skills selected for it and loads their detailed content when needed.

Note

A skill normally contains SKILL.md and may include scripts/, references/ or assets/.

The operator selects one installation-wide execution environment for shell commands and skill scripts:

  • Host runs them directly on the machine running Oscova and is the default.
  • Disabled prevents skill scripts and shell commands from running.
  • Docker runs them inside the configured Docker sandbox.
  • Microsoft MXC uses native operating-system isolation when its prerequisites are available.
Caution

Host commands use Oscova's operating-system account permissions. Auto-approved shell commands run without a human prompt, and offline runs reject host execution because it cannot guarantee no egress.

  • File tools and shell tools can use the same approved files without sharing an execution process. File tools resolve and validate paths on the host. In Docker execution, the shell sees those same files through bind mounts.
  • Agents can also receive approval-governed tools for creating or updating markdown-only skills. Successful changes become available to later runs.

Prepare chat and automation

Before using an agent, review this chain:

  • Instructions define what the agent should do.
  • Tools define what it can call.
  • Skills supply task-specific guidance.
  • Workspace grants define which files it can reach.
  • Privacy and governance controls narrow those capabilities at runtime.

Interactive chat can ask before approval-required calls and shows the target plus expanded arguments for shell or skill-script execution. Scheduled tasks cannot pause for a person, so each task must explicitly auto-approve or auto-reject those calls. Review its agent, run scope, tools and file grants before enabling it.