agentc
GitHubagentc-sh/agentc
agentc
GitHubagentc-sh/agentc
›Introduction
Get started›Concepts in 5 minutes›Build your first agent›Add your first tool›Serve and connect
Concepts›Architecture overview›The manifest›The compilation pipeline›Archetypes›The graph›Tools and capabilities›Runtime libraries›Skills›Agents and prompts›Serving and protocols›Observability
Guides›Author a manifest›Write a tool›Give your agent a filesystem›Control network egress›Connect external tools via MCP›Connect agents via A2A›Use the bash tool›Control tool access with capabilities›Write templated prompts›Manage prompts with Langfuse›Pass context from the client›Configure a model provider›Connect a CopilotKit frontend›Deploy a standalone binary›Deploy with Docker and PostgreSQL›Instrument with OpenTelemetry›Extend code generation with blocks
Reference
Manifest
Runtime
ReAct
HTTP
›Prompt templates›State
›Observability

Prompt templates

The variables the ReAct graph injects into the system prompt.

The ReAct graph injects the following variables into the agent's system prompt before each run. Reference them with Jinja2 syntax, for example {{ agent_name }}. The set of available variables is graph-dependent, so it is documented here alongside the graph that provides it. See Write templated prompts for usage patterns.

VariableTypeDescription
agent_namestringThe agent's name, taken from the agent block label in the manifest.
skillslistThe skills available to the agent. Each entry carries the skill's name and description.
context_varsobjectThe context variables supplied by the client for this run, keyed by name.
current_datetimestringThe current date and time captured at the start of the run.

Variables are injected at runtime before each run, so a template can react to the client-supplied context of the current request. The prompt field itself is declared on the agent block.

← PreviousCheckpointsNext →State

© 2026 pogue.dev. All rights reserved.

Creative CommonsCC BY 4.0

Search docs

Search the agentc documentation