chore: enforce token efficiency rules across all agent instruction files

[dnim]

No description provided.

[codecov]

Codecov Report

✅ All modified and coverable lines are covered by tests.
✅ Project coverage is 83.67%. Comparing base (dbca48c) to head (77588ad).
⚠️ Report is 1 commits behind head on main.

Additional details and impacted files

@@           Coverage Diff           @@
##             main      #28   +/-   ##
=======================================
  Coverage   83.67%   83.67%           
=======================================
  Files           9        9           
  Lines         674      674           
  Branches      173      163   -10     
=======================================
  Hits          564      564           
  Misses        110      110           

☔ View full report in Codecov by Sentry.
📢 Have feedback on the report? Share it here.

🚀 New features to boost your workflow:

• ❄️ Test Analytics: Detect flaky tests, report on failures, and find test suite problems.
• 📦 JS Bundle Analysis: Save yourself from yourself by tracking and limiting bundle sizes in JS merges.

[Copilot]

Pull request overview

This PR centralizes and standardizes “token efficiency” guidance across agent-facing instruction surfaces, and wires core instruction docs into the OpenCode configuration so agents consistently receive the same rules.

Changes:

• Add an instructions include list and per-mode agent model configuration to opencode.json.
• Add “Token Efficiency” rules to canonical workflow docs and agent entrypoints (AGENTS/GEMINI).
• Tighten the AntiVibe skill guidance to be more concise/direct.

Reviewed changes

Copilot reviewed 5 out of 5 changed files in this pull request and generated no comments.

Show a summary per file

File	Description
opencode.json	Adds instruction includes and defines agent mode model/temperature/step settings.
GEMINI.md	Reworks Gemini-facing context to emphasize token-efficiency rules and point to .opencode/docs/.
AGENTS.md	Adds shared token-efficiency rules and clarifies OpenCode vs non-OpenCode workflow guidance.
.opencode/skills/antivibe/SKILL.md	Makes AntiVibe output requirements more concise and explicit.
.opencode/docs/AGENT_WORKFLOW.md	Adds token-efficiency rules as an explicit top-level section in the canonical workflow doc.

---

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

[dnim]

@copilot resolve the merge conflicts in this pull request

[dnim]

@copilot resolve the merge conflicts in this pull request

make sure to take opencode.json configuration from main branch

[Copilot]

@copilot resolve the merge conflicts in this pull request

make sure to take opencode.json configuration from main branch

Resolved in 77588ad. Merged main into the branch — took the full model/agent configuration from main (gpt-5.1-codex default + per-agent gemini/codex models) and kept only the instructions array addition from this PR.