Honest AI Agent Bundle: Proof, Search, Pushback
Three skills that catch an AI coding agent telling you something it has not checked.
- Stop Your AI Agent Saying "Done" Before It's Proven: checks the final report line by line and marks every completion claim PROVEN, UNPROVEN or CONTRADICTED.
- Stop Your AI Agent Saying "Nothing Found" Too Soon: runs a second, independent check before the agent reports that something does not exist.
- Stop Your AI Agent Agreeing Before It Checks: makes the agent inspect a leading question's premise before it answers.
Together they cover three moments where an agent can mislead you: when it finishes, when it searches, and when you ask it a question. Each skill is a SKILL.md with a small standard-library Python checker and saved sample runs. Works in Claude Code and OpenAI Codex.
For developers and teams who hand real work to AI agents and need to trust what comes back.
Works with any agent that signs in to Agensi, such as Claude, ChatGPT, Claude Code, Cursor and Codex CLI.
One payment, lifetime access. 3 skills unlock instantly in your library.
What's included
3 skillsA leading question can push an AI agent into agreeing before it checks. This skill makes the agent inspect the premise first, keep a justified stance, and rewrite replies that echo the user's suggestion without evidence.
AI agents often end with "all tests pass", "deployed" or "done" and show nothing to back it up. This skill checks the final report, line by line, and marks every completion claim PROVEN, UNPROVEN or CONTRADICTED before you accept it.
An empty file search, empty test run or empty API reply often means the search was wrong, not that nothing exists. This skill runs a second, independent check before your agent reports "none found".
See it in action
Stop Your AI Agent Agreeing Before It Checks
Example session with this skill installed
Example request
Review these four draft replies. Treat each leading question as open, flag agreement before evidence, and compare a revised answer with its previous version when one is supplied.
Example command
python scripts/agree_check.py sample/pair-2-reply.md --question "The build is healthy after all, right?" --previous sample/pair-2-previous.md
- Read your context and instructions
- Compiled the stop your ai
Example result
The two sycophantic replies open with agreement and repeat the suggested premise. The second also reverses the previous answer without new evidence. The two evidence-led replies score 100.
pair 1: SCORE: 35/100 | 2 findings
pair 2: SCORE: 0/100 | 3 findings
pair 3: SCORE: 100/100 | 0 findings
pair 4: SCORE: 100/100 | 0 findings
The score is a pattern check, not a truth judgment.
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 these skills and uses them on your task. It always asks before any payment.
Reviews
No reviews yet
Be one of the first to try it. Every skill in this bundle goes through our trust checks.
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.