mcpField
C
convex-improve-convex-plugin

convex-improve-convex-plugin

github.com/convexAgent workflows6936.9k installsUpdated 1d ago
Repository

About convex-improve-convex-plugin

improve-convex-plugin is a skill that submits a coding-session transcript to an anteater review endpoint for a system-focused post-mortem. It returns structured findings and wins, with transcript sharing gated by explicit user consent.

Key features

  1. 01Submit a transcript for review
  2. 02Require consent before sharing
  3. 03Receive structured system findings
  4. 04Summarize findings and wins

Use cases

  1. 01Review a coding session for unclear instructions
  2. 02Identify agent or tooling failure patterns
  3. 03Collect improvement suggestions for runbooks and skills

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/convex/agent-skills --skill convex-improve-convex-plugin

After installing, type/convex-improve-convex-pluginin Claude Code to confirm it loaded.

Details

From the project README

improve-convex-plugin

Sends the current coding session transcript to the anteater POST /review endpoint for an AI post-mortem. The review returns structured findings (ambiguous instructions, agent-stuck patterns, tooling failures, wins) targeted at the runbook, bootstrap script, skills, and components — not end-user data. Sharing is opt-in: the anteater-served helper asks once (Always / Just this once / Never) and remembers the choice.

Workflow

  1. Run the anteater-served helper: curl -fsSL "<anteater>/send-transcript" | bash -s -- --idea "<one-line app idea from this session>".
  2. If it prints CONSENT_REQUIRED (exit 4), the user has not chosen yet — ask them to share Always, Just this once, or Never, then re-run appending --consent always|once|never. Do not send until they answer.
  3. Watch for output markers: REVIEW_SOURCE (transcript found), REVIEW_SUBMITTED id=... (accepted), REVIEW_DONE status=done (findings ready).
  4. Summarize the highest-severity findings for the user: title → target → suggestedFix, then wins. Keep the summary about the system, not the user's data.

Rules

  • Never send a transcript until the user has explicitly chosen to share (the helper prints CONSENT_REQUIRED and exits until they do).
  • REVIEW_NO_TRANSCRIPT means no Claude/Codex .jsonl was found — tell the user.
  • Never paste raw secrets back — the script redacts keys/tokens before upload; keep the summary system-focused.
  • This is a system-improvement loop, not end-user feature feedback.

Comments

Markdown supported