Check compiled Bindry skills against their source Binder and report which are current, stale, live, or unverifiable. This read-only check makes no edits or updates; use the sync skill separately to refresh stale skills.
Report which compiled Bindry skills are stale, without changing anything. Use when the user asks to check for drift, staleness, or whether their Bindry skills are up to date.
Run score Not tested
See how to installReview the instructions the agent will receive before you install.
Check whether the skills already compiled by the bindry-sync skill in this project have fallen behind the
Bindry Binder they came from. This is read-only — it never edits, deletes, or re-syncs a skill, only reports.
Invoke explicitly with $bindry-check, or let it trigger automatically when the user asks about drift/staleness.
bindry.config.json in the project root (written by a previous sync) to know which Binder, API
base to check against. If it's missing, tell the user to use the bindry-sync skill at least once first,
then stop.--token <api-key> (generated from the workspace's team page in Bindry, not
Account settings) or the BINDRY_API_TOKEN environment variable — same requirement as bindry-sync.bindry@<marketplace>), then run:
node <resolved-plugin-root>/scripts/check-drift.mjs [--dir .agents/skills] [--api-base <url>] [--token <api-key>]
If you can't locate scripts/check-drift.mjs under this plugin's installed root, stop and say so plainly
rather than guessing a path.--mode live — always current by design, calls the MCP server
directly, never goes stale), and which it couldn't check (no pin or live comment, e.g. a hand-authored
skill, or a Skill no longer in the Binder). If it failed with an authentication error, say so plainly
rather than retry or guess.bindry-sync skill to update it — this skill never does that
for them. Live skills never need this — don't suggest re-syncing them just because they showed up in the
report.Note on "how far behind": the API doesn't expose full version history for a Skill today, only its current pinned version, so the report names the two version strings on each side (e.g. "compiled at 1.0.0, Binder now pins 2.0.0") rather than a version count. Don't invent a count if asked — say this isn't available yet.
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.