opus-gemini-lite
Switch the Claude Code orchestration mode to opus-gemini-lite.
Skill by tahmidulferdous
Chalk Labs
Need help deploying opus-gemini-lite?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/tahmidulferdous-opus-gemini-lite
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: agent-building
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/opus-gemini-lite
What's inside
- Skill name
opus-gemini-lite- Description
- Switch the Claude Code orchestration mode to opus-gemini-lite. Quality first: Opus plans, writes precise instructions, reviews every diff and runs all verification; Gemini only follows instructions.
- License
- MIT
- Instructions
- 15 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# opus-gemini-lite | Opus | Gemini | |------|--------| | Plans, writes step-level instructions, reviews every diff line by line, runs all tests and checks | Writes the code and tests exactly as instructed | Mode file now reads: !`mkdir -p ~/.claude && echo gemini-lite > ~/.claude/exec-mode && cat ~/.claude/exec-mode` If the line above does not show `gemini-lite`, run `echo gemini-lite > ~/.claude/exec-mode` with Bash. Then confirm to the user in one line: "Mode: opus-gemini-lite. Quality first: Opus plans, writes precise instructions, reviews every diff and runs all verification; Gemini only follows instructions." The mode applies from the next prompt and persists across sessions (the `opus-gemini-orchestrator` hook injects it into every prompt). For how to work in this mode, load the `opus-gemini-orchestrator` skill.
From tahmidulferdous/opus-gemini-orchestrator, MIT.
More from tahmidulferdous/opus-gemini-orchestrator
- 0.552score
opus-gemini-orchestrator
tahmidulferdous
Claude Opus plans, instructs and verifies while Gemini (Antigravity CLI `agy`) writes code, writes and runs tests, reviews, and does deep web research, to cut…
SkillBFreshness: B★ 1Claude Code +9 - 0.539score
opus-gemini-deepresearch
tahmidulferdous
Switch the Claude Code orchestration mode to opus-gemini-deepresearch.
SkillBFreshness: B★ 1Claude Code +9 - 0.539score
opus-gemini-full
tahmidulferdous
Switch the Claude Code orchestration mode to opus-gemini-full.
SkillBFreshness: B★ 1Claude Code +9 - 0.539score
opus-gemini-mid
tahmidulferdous
Switch the Claude Code orchestration mode to opus-gemini-mid.
SkillBFreshness: B★ 1Claude Code +9 - 0.539score
opus-sonnet
tahmidulferdous
Switch the Claude Code orchestration mode to opus-sonnet.
SkillBFreshness: B★ 1Claude Code +9 - 0.536score
opus-solo
tahmidulferdous
Switch the Claude Code orchestration mode to opus-solo.
SkillBFreshness: B★ 1Claude Code +9
Signals
- Stars
- 1
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Sep 17, 2026 (1 month ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from tahmidulferdous
- 0.552score
opus-gemini-orchestrator
tahmidulferdous
Claude Opus plans, instructs and verifies while Gemini (Antigravity CLI `agy`) writes code, writes and runs tests, reviews, and does deep web research, to cut…
SkillBFreshness: B★ 1Claude Code +9 - 0.539score
opus-gemini-deepresearch
tahmidulferdous
Switch the Claude Code orchestration mode to opus-gemini-deepresearch.
SkillBFreshness: B★ 1Claude Code +9 - 0.539score
opus-gemini-full
tahmidulferdous
Switch the Claude Code orchestration mode to opus-gemini-full.
SkillBFreshness: B★ 1Claude Code +9 - 0.539score
opus-gemini-mid
tahmidulferdous
Switch the Claude Code orchestration mode to opus-gemini-mid.
SkillBFreshness: B★ 1Claude Code +9 - 0.539score
opus-sonnet
tahmidulferdous
Switch the Claude Code orchestration mode to opus-sonnet.
SkillBFreshness: B★ 1Claude Code +9 - 0.536score
opus-solo
tahmidulferdous
Switch the Claude Code orchestration mode to opus-solo.
SkillBFreshness: B★ 1Claude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get opus-gemini-lite running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
opus-gemini-lite skill. Agent Mart. https://agentmart.dev/skills/tahmidulferdous-opus-gemini-lite (last updated 2026-10-24)