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/maxferalten-ecomode
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
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/ecomode
What's inside
- Skill name
ecomode- Description
- Token-efficient model routing modifier
- License
- MIT
- Instructions
- 71 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# Ecomode Skill Token-efficient model routing. This is a **MODIFIER**, not a standalone execution mode. ## What Ecomode Does Overrides default model selection to prefer cheaper tiers: | Default Tier | Ecomode Override | |--------------|------------------| | THOROUGH | STANDARD, THOROUGH only if essential | | STANDARD | LOW first, STANDARD if needed | | LOW | LOW - no change | ## Combining with Other Modes Ecomode combines with execution modes: | Combination | Effect | |-------------|--------| | `eco ralph` | Ralph loop with cheaper agents | | `eco ultrawork` | Parallel with cheaper agents | | `eco autopilot` | Full autonomous with cost optimization | ## Routing Rules **ALWAYS prefer lower tiers. Only escalate when genuinely required.** | Decision | Rule | |----------|------| | DEFAULT | Start with LOW tier for most tasks | | UPGRADE | Escalate to STANDARD when LOW fails | | AVOID | THOROUGH - only for planning if essential | ## Agent Selection Ecomode preference order: ``` // PREFERRED - Use for most tasks delegate(role="executor", tier="LOW", task="...") delegate(role="explore", tier="LOW", task="...") // FALLBACK - Only if LOW fails delegate(role="executor", tier="STANDARD", task="...") // AVOID - Only for planning/critique delegate(role="planner", tier="THOROUGH", task="...") ``` ## Token Savings Tips 1. Batch similar tasks to one agent 2. Use explore (LOW) for file discovery 3. Prefer LOW-tier for simple changes 4. Use writer (LOW) for documentation 5. Avoid THOROUGH unless essential ## State Management ``` State: ecomode - active: boolean ``` ## Keywords - eco, ecomode, save tokens - cost efficient, cheap mode
From MaxFerAlten/tenderclaw, MIT.
More from MaxFerAlten/tenderclaw
- 0.404score
ralph
MaxFerAlten
Autonomous execution loop that never stops until task completion with architect verification
SkillDFreshness: DClaude Code +9 - 0.404score
brainstorming
MaxFerAlten
Design-first workflow with HARD-GATE — no code until design is approved
SkillDFreshness: DClaude Code +9 - 0.404score
ralplan
MaxFerAlten
Consensus planning via Planner + Architect + Critic triad before execution
SkillDFreshness: DClaude Code +9 - 0.401score
team
MaxFerAlten
N coordinated agents on shared task list with team pipeline
SkillDFreshness: DClaude Code +9 - 0.401score
security-review
MaxFerAlten
Security audit for vulnerabilities
SkillDFreshness: DClaude Code +9 - 0.401score
tdd
MaxFerAlten
Test-driven development workflow
SkillDFreshness: DClaude Code +9 - 0.401score
doctor
MaxFerAlten
Diagnose and fix TenderClaw installation issues
SkillDFreshness: DClaude Code +9 - 0.401score
plan
MaxFerAlten
Strategic planning with requirements gathering
SkillDFreshness: DClaude Code +9 - 0.401score
cancel
MaxFerAlten
Cancel any active workflow mode
SkillDFreshness: DClaude Code +9 - 0.401score
analyze
MaxFerAlten
Run deep investigation with evidence-based findings
SkillDFreshness: DClaude Code +9 - 0.401score
code-review
MaxFerAlten
Conduct thorough code review with structured feedback
SkillDFreshness: DClaude Code +9 - 0.398score
deepsearch
MaxFerAlten
Thorough codebase search
SkillDFreshness: DClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Apr 7, 2026 (6 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/MaxFerAlten/tenderclaw
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from MaxFerAlten
- 0.404score
ralplan
MaxFerAlten
Consensus planning via Planner + Architect + Critic triad before execution
SkillDFreshness: DClaude Code +9 - 0.404score
brainstorming
MaxFerAlten
Design-first workflow with HARD-GATE — no code until design is approved
SkillDFreshness: DClaude Code +9 - 0.404score
ralph
MaxFerAlten
Autonomous execution loop that never stops until task completion with architect verification
SkillDFreshness: DClaude Code +9 - 0.401score
cancel
MaxFerAlten
Cancel any active workflow mode
SkillDFreshness: DClaude Code +9 - 0.401score
security-review
MaxFerAlten
Security audit for vulnerabilities
SkillDFreshness: DClaude Code +9 - 0.401score
tdd
MaxFerAlten
Test-driven development workflow
SkillDFreshness: DClaude Code +9
Cite this page
ecomode skill. Agent Mart. https://agentmart.dev/skills/maxferalten-ecomode (last updated 2026-10-24)