Set up a machine-level connection between Codex and the Bindry MCP server. This one-time configuration enables compiled Bindry skills to use live content, with an API key and the Bindry API base URL.
One-time setup connecting Codex to the Bindry MCP server, for live-mode skills. Use when the user wants to enable live mode for Bindry skills or asks to connect Codex to Bindry's MCP server.
Run score Not tested
See how to installReview the instructions the agent will receive before you install.
Connect this machine to the Bindry MCP server so --mode live skills (compiled by the bindry-sync skill)
actually work. This is a one-time, per-machine/user step — it isn't tied to any particular project or Binder,
and only needs to happen once even if the user syncs several Binders live later.
bindry-sync works here
too, no separate scope or permission to grant. Generate one from the workspace's team page in Bindry (not
Account settings — a key is scoped to whichever workspace's team page made it). Recommend the user put it
in a BINDRY_API_TOKEN environment variable rather than pasting it directly.--api-base <url> (the Bindry API's base URL — ask if not obvious from context, e.g. from an existing
bindry.config.json in a project this user has already synced).codex mcp add bindry --url <api-base>/api/mcp --bearer-token-env-var BINDRY_API_TOKEN
bindry's
status). If it reports a connection failure, report exactly what it said (bad API base, network issue, or
an invalid/expired key show up as different failures — don't guess which without checking).--mode live will now
compile skills the agent can actually call MCP tools through, and the bindry-check skill will report them
as "live (always current)" rather than stale or unknown.No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
Plan worthwhile local tasks by checking dependencies, effects, resources, and platform boundaries, then execute the exact approved plan. It can use safe parallel work or suitable Apple-silicon backends when the project exposes them.
Record deferred engineering decisions and temporary workarounds in a debt registry, with context such as effort, ongoing cost, affected area, and payoff trigger. Entries receive short labels so they can be reviewed or dropped later.
Generate or compare AI agent code for LangChain, EINO, AutoGen, AgentScope, and CrewAI using framework-specific templates, API mappings, conventions, and project structures. Reference files include verification dates to help identify potentially outdated guidance.
Investigate a reproducible bug, test failure, or unexpected page behavior, then make a narrowly scoped fix. The workflow calls for a regression test before changing code, verifies the fix, and reports remaining risks and evidence while avoiding unrelated refactoring or feature work.
Build an AI agent project through six collaborative stages, from requirements and architecture to tools, prompts, code generation, and verification. Start framework-independent, then generate a runnable project for frameworks such as LangChain, EINO, AutoGen, AgentScope, or CrewAI.
Audit a project or learning workflow for scope drift, conflicting plans, inconsistent names, and code quality concerns. The skill reads project files and code, then reports evidence, severity, and suggested next steps without changing files.