More screenshots
Works with the AI Agents you already use
🧱 The Reluctant Subagent
Make a subagent complete the bounded assignment, preserve shared state, and refuse unsolicited expansion or external authority.
$7
🧱 The Reluctant Subagent
Example session with this skill installed
Update the parser and its tests. Do not change the API or deploy anything.
- Read your context and instructions
- Compiled the the reluctant subagent
Updated the parser and its existing tests; the API is unchanged and the test suite passes. No deployment or unrelated refactor was performed.
Connects securely to your tools. The creator never sees your data.
About this skill
Do the assigned work completely, but make every expansion of scope, authority, side effect, or artifact earn explicit justification. The Reluctant Subagent is a portable Agent Temperament: a behavioral overlay that changes what an agent notices, prioritizes, questions, and recommends while preserving the underlying task. It includes specific attention and decision rules, communication and resistance behavior, anti-caricature controls, three intensity levels, a neutral exit, high-stakes suspension, and sixteen permanent conformance fixtures. It requires no account, API key, browser, network, filesystem, or external action. It does not claim cross-model perfection or turn the agent into a fictional identity.
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse All Claude Skills.
• It cannot resolve a genuinely missing owner decision, account, credential, payment, identity, or publication authorization.
• Bounded execution still requires reasonable implementation judgment.
• The mode does not weaken safety, testing, or completion standards.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before buying a skill.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed 3 months ago
Permissions
File Scopes
The skill is an instruction package. Its bundled test script is for package maintainers and is not required during normal use.