Skip to main content
Glama
ajmainapon

One Agent Harness

by ajmainapon

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
GROK_HOMENoGrok Build CLI data directory (alternative to HARNESS_GROK_HOME). Default: ~/.grok~/.grok
CODEX_HOMENoOpenAI Codex data directory (alternative to HARNESS_CODEX_HOME). Default: ~/.codex~/.codex
HARNESS_HOMENoOne Agent Harness state, logs, and checkpoints. Default: ~/.harness~/.harness
ANTIGRAVITY_HOMENoAntigravity data directory (alternative to HARNESS_AGY_HOME). Default: ~/.gemini/antigravity~/.gemini/antigravity
HARNESS_AGY_HOMENoAntigravity data directory (alternative to ANTIGRAVITY_HOME). Default: ~/.gemini/antigravity~/.gemini/antigravity
CLAUDE_CONFIG_DIRNoClaude Code data directory (alternative to HARNESS_CLAUDE_HOME). Default: ~/.claude~/.claude
HARNESS_GROK_HOMENoGrok Build CLI data directory (alternative to GROK_HOME). Default: ~/.grok~/.grok
HARNESS_CODEX_HOMENoOpenAI Codex data directory (alternative to CODEX_HOME). Default: ~/.codex~/.codex
HARNESS_CLAUDE_HOMENoClaude Code data directory (alternative to CLAUDE_CONFIG_DIR). Default: ~/.claude~/.claude

Instructions

Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.

This server publishes no instructions, or was last inspected before Glama recorded them.

Capabilities

Features and capabilities supported by this server

Protocol revision2025-11-25

CapabilityDetails
tools
{}

Tools

Functions exposed to the LLM to take actions

NameDescription
pull_handoff_contextA

Pull the exact context (verbatim recent conversation turns, implementation plans, task checklists, modified/read files, terminal commands/errors, and git state) from the user's previous session in Claude Code, Antigravity, Codex, or Grok Build CLI. Also returns a snapshot of the latest active sessions across all other platforms. Call this whenever the user says '/handoff', '$handoff', 'continue from my last session', or switches from another agent.

list_recent_sessionsB

List recent coding sessions across Claude Code, Antigravity, Codex, and Grok Build CLI with session IDs, titles, working directories, turn counts, and timestamps.

search_cross_agent_historyA

Search across all 4 agents' conversation transcripts, plans, and modified file paths for a keyword, error message, or filename.

save_checkpoint_noteA

Save an explicit checkpoint summary and next steps so the next agent you open receives it at the top of its handoff context.

inject_session_to_agentB

Convert and inject the latest context bundle directly into a target agent's native session store ('claude', 'codex', 'antigravity', or 'grok') so it can be resumed natively.

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

TDQS

A3.7/5.0

Scored across 5 tools

Disambiguation4/5

Each tool targets a distinct action: pull context, list sessions, search history, save checkpoint, and inject into an agent. There is minor overlap between pull_handoff_context (which also returns an active session snapshot) and list_recent_sessions, but the descriptions clarify their primary purposes.

Naming Consistency5/5

All tools follow a consistent snake_case, verb-first convention (pull_, list_, search_, save_, inject_). The prepositional suffix in inject_session_to_agent is a slight variation but remains readable and predictable.

Tool Count5/5

Five tools is well-scoped for a cross-agent handoff harness, with each tool covering a necessary operation (pull, list, search, save, inject). There is no redundancy or obvious missing tool at this scale.

Completeness4/5

The toolset covers the core lifecycle: reading context (pull, list, search) and writing/injecting (save checkpoint, inject). Minor gaps exist, such as updating or deleting saved checkpoint notes, but agents can work around these.

Maintenance

ActivityMaintained
ResponsivenessNo issues