Agent Tools
Infrastructure for coding agents: how they message each other, what they know, what they are allowed to run, and the servers they call.
See also: Command Line Tools , Development Tools
Coordination
How independent agent sessions reach each other and avoid working over one another.
-
Local coordination for coding-agent sessions across projects and harnesses: durable mail, path claims, work leases, and obligations that record who owes whom a decision, a fix, or a finished job. Formerly agent-mail.
-
A machine-local, agent-writable knowledge base where coding-agent sessions record and search hard-won facts about tools and workflows, with git provenance, talk pages, and a session ledger.
-
PATH-level command wrappers that apply workstation policy to ssh, scp, rsync, git, and uv inside coding-agent sessions, including Jujutsu interoperability and a memory ceiling for uv run.
-
A PreToolUse hook for Claude Code, Codex, Kimi, and opencode that decides Bash tool requests against local development and research conventions, denying what a general permission system cannot infer.
-
Launchers for Claude Code, Codex, Kimi, opencode, OMP, and agy that start each agent under agent-command-guards, with stable session identity, model-first commands, resume by name or transcript text, cross-harness continuation, crash recovery, and exit receipts.
-
Runs a coding agent as a job under an explicit tool policy (no tools, read-only, or confined writes), with process containment, cost limits, and a record of what the agent was given and what it did. Optionally submits the work as a Weft job.
-
Sends a coding task to an agent on another machine. The agent edits a snapshot of the source tree as a Weft job, and its work comes back as a diff to verify and apply.
-
An MCP server that converts timestamps with IANA time zone rules and reports date-boundary changes.