← Back to context

Comment by postalcoder

12 hours ago

That's not the only useful takeaway. I found this to be true:

  > "Explore project first, then invoke skill" [produces better results than] "You MUST invoke the skill".

I recently tried to get Antigravity to consistently adhere to my AGENTS.md (Antigravity uses GEMINI.md). The agent consistently ignored instructions in GEMINI.md like:

- "You must follow the rules in [..]/AGENTS.md"

- "Always refer to your instructions in [..]/AGENTS.md"

Yet, this works every time: "Check for the presence of AGENTS.md files in the project workspace."

This behavior is mysterious. It's like how, in earlier days, "let's think, step by step" invoked chain-of-thought behavior but analogous prompts did not.

6 comments

postalcoder

Reply
Izkata  10 hours ago

An idea: The first two are obviously written as second-person commands, but the third is ambiguous and could be interpreted as a first-person thought. Have you tried the first two without the "you must" and "your", to also change them to sort-of first-person in the same way?

  • postalcoder  9 hours ago

    Solid intuition. Testing this on antigravity is a chore because I'm not sure if I have to kill the background agent to force a refresh of the GEMINI.md file so I just did it anyway.

      +------------------+------------------------------------------------------+
  | Success/Attempts | Instructions                                         |
  +------------------+------------------------------------------------------+
  | 0/3              | Follow the instructions in AGENTS.md.                |
  +------------------+------------------------------------------------------+
  | 3/3              | I will follow the instructions in AGENTS.md.         |
  +------------------+------------------------------------------------------+
  | 3/3              | I will check for the presence of AGENTS.md files in  |
  |                  | the project workspace. I will read AGENTS.md and     |
  |                  | adhere to its rules.                                 |
  +------------------+------------------------------------------------------+
  | 2/3              | Check for the presence of AGENTS.md files in the     |
  |                  | project workspace. Read AGENTS.md and adhere to its  |
  |                  | rules.                                               |
  +------------------+------------------------------------------------------+

    In this limited test, seems like the first person makes a difference.

    • vidarh  7 hours ago

      Thanks for this (and to Izkata for the suggestion). I now have about 100 (okay, minor exaggeration, but not as much as you'd like it to be) AGENTS.md/CLAUDE.md files and agent descriptions I will want to systematically validate if shifting toward first person helps adherence for...

      I'm realising I need to start setting up an automated test-suite for my prompts...

      1 reply →

    • naasking  2 hours ago

      That's really interesting. I ran this scenario through GPT-5.1 and the reasoning it gave made sense, which essentially boils down to: in tools like Claude Code, Gemini Codex, and other “agentic coding” modes, the model isn’t just generating text, it’s running a planner, and the first-person form conforms to the expectation of a step in a plan, where the other modes are more ambiguous.