Files
Wesam Abousaid a3f328c043 docs: refresh for OpenCode v1.17.13, add Go coverage, and rebrand
- Bump every version pin, pricing table, and model ID to the verified
  2026-07-05 state (v1.17.13): Claude Fable 5 / Sonnet 5 on Zen, new
  free tier, deprecation sunset table, v1.17.x changelog section
- Cover gaps: OpenCode Go vs Zen billing, Anthropic subscription-login
  removal (PR #18186), MCP resources, --mini mode, --auto flag, yolo mode
- Fix correctness bugs: command-template !`cmd` syntax in docs and
  .opencode/commands, protect-secrets regex missing 'cat .env', dual
  plugin exports, quickstart PATH fix, Playwright MCP flags, ctrl+d
  keybind conflict, agent/command required-field claims
- Fix links: cursor.com, windsurf.com, platform.claude.com,
  code.claude.com, opencode.ai/discord, Vercel Grep announcement
- Rebrand: banner (Images/banner.svg), 1280x640 social preview asset,
  hero redesign with star CTA, ecosystem stats, private vulnerability
  reporting channel, CI-matching local checks, MD060 lint opt-out
2026-07-05 14:11:51 +02:00

1.2 KiB

description, agent
description agent
Run the project test suite and triage any failures build

Run the project test suite and triage failures.

  1. Detect the runner from the repo and run it:

!cat package.json 2>/dev/null | grep -E '"test"|"scripts"' | head -5

Pick the right command:

  • pnpm test, npm test, yarn test for Node
  • pytest / python -m pytest for Python
  • go test ./... for Go
  • cargo test for Rust
  • Other: read the project's AGENTS.md for the canonical command
  1. Run the chosen test command with the bash tool and capture the output. (Shell injections like the one above expand before the model runs, so the command you picked in step 1 has to be run as a normal tool call, not a template.)

  2. If everything passes, print a one-line summary and stop.

  3. If there are failures:

    • Group them by file
    • For each failing test, open the relevant source and identify the root cause
    • Propose a fix (snippet) but do not edit files yet — wait for user approval
    • Distinguish between "test is wrong" and "code is wrong"
  4. After the user confirms, apply the fixes and re-run the suite to verify.

Extra arguments (passed to the runner): $ARGUMENTS