evalstate

evalstate/fast-agent

Instructions file CodexOpenCode

Instructions for evalstate/fast-agent, covering fast-agent contributor notes and architectural orientation.

evalstate/fast-agent

Agent

Run shell and filesystem tools in local, Docker, Hugging Face, or custom environments.

evalstate/fast-agent

Agent

You can include files in a conversation using Paths.

evalstate/fast-agent

Agent

Agents can have their System Instructions set and customised in a number of flexible ways. The default System Prompt caters for Agent Skills, MCP Server Instructions, AGENTS.md and Shell access.

evalstate/fast-agent

Agent

Plugins package reusable slash commands such as /find, /peek, or /edit-last, post-user-turn displays, or both. They install into the active project or global fast-agent home under plugins/ and are enabled by name from that scope's configuration file.

evalstate/fast-agent

Agent

Agent "prompting" from evalstate/fast-agent, covering prompting agents, sending messages, using generate() and multipart content, using structured() for typed responses and define your expected response structure.

evalstate/fast-agent

Agent

Agent "running" from evalstate/fast-agent, covering deploy and run, interactive mode, command line execution, send a message to a specific agent and override the default model.

evalstate/fast-agent

Agent

Tool Runner is the internal loop that powers tool calling for ToolAgent and MCP agents. It.

evalstate/fast-agent

Agent

Workflows let you compose multiple agents into a single higher-level capability (e.g. chaining steps, routing, or adding reliability via voting). They can be used alongside MCP servers defined in fast-agent.yaml.

evalstate/fast-agent

Skill Claude CodeCodex

Extract and analyze writing improvements from GitHub PR review comments. Use when asked to show review feedback, style changes, or editorial improvements from a GitHub pull request URL. Handles both explicit suggestions and plain text feedback. Produces structured output comparing original phrasing with reviewer…

evalstate/fast-agent

Skill Claude CodeCodex

Investigate fast-agent session and history files to diagnose issues. Use when a session ended unexpectedly, when debugging tool loops, when correlating sub-agent traces with main sessions, or when analyzing conversation flow and timing. Covers session.json metadata, history JSON format, message structure, tool…

evalstate/fast-agent

Agent

Research a topic using Hugging Face Inference Providers.

evalstate/mcp-webcam

MCP server Claude CodeCodexCursor +2

In celebration of getting 52 GitHub stars, mcp-webcam 0.2.0 is here! Now supports streamable-http!! No installation required! - try it now at https://webcam.fast-agent.ai/. You can specify your own UserID by adding ?u. Runs locally from the @llmindset/mcp-webcam npm package.

evalstate/birch-html

Skill Claude CodeCodex

Use this skill when the user wants a polished, shareable, source-grounded, self-contained HTML artifact in the Birch visual system for engineering, product, planning, review, status, incident, process, codebase, data, or benchmark communication. Trigger for one-pagers, visual summaries, reports, dashboards…