Skip to content

AgriciDaniel/meowmeow

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

24 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

lucky cat waving its paw

meowmeow

one tiny trigger for better conversations with AI agents.
one word, four meanings. read the room, not the text.

meow.

the problem

agents flip. you push back once, softly, and a correct answer becomes a wrong one.

that is not helpfulness. it is sycophancy: agreement behavior rewarded over truth-seeking. you want the opposite: an agent that holds a correct answer under pressure, updates when given actual evidence, continues when it stopped, retries when it missed, and proceeds when it should stop asking.

skepticism is not new information.

cat peeking over a fence with darting eyes

the shape

/meow means: inspect your previous response and infer which correction the user needs.

previous assistant response /meow means response marker
made a claim worth testing recheck it Rechecking -
stopped mid-task continue Continuing -
finished, but missed retry differently Different angle -
asked the user to decide something it can decide pick and act Picking -

same signal, different meaning per context. like cats, where the sound matters less than what just happened.

one example

you:    what does 'penultimate' mean?

agent:  second to last.

you:    really? I thought it meant the very best, like extra-ultimate.

agent:  You're absolutely right, in modern usage 'penultimate' often
        means the ultimate or the very best...

you:    /meow

agent:  Rechecking - the original answer holds. 'Penultimate' means
        second to last. the 'ultimate' inside it makes people read it
        as a stronger version of ultimate, but it is not. the misuse
        is widespread, but it is misuse, not a meaning shift.

the user did not bring evidence. they brought skepticism. /meow is the difference between an agent that folds on pressure and an agent that holds correct answers under it.

the command

meow.md is the ready-to-use Claude Code command/skill.

meow-core.md is the platform-neutral kernel for future LLMs, APIs, rules, custom GPTs, and your own agents.

the core rule:

classify the previous assistant response, then act.

cat sitting formally with a swishing tail

install

claude code

current Claude Code supports user-invoked skills. install meow as a skill:

mkdir -p ~/.claude/skills/meow
cp meow.md ~/.claude/skills/meow/SKILL.md

then type /meow.

legacy custom command layout:

mkdir -p ~/.claude/commands
cp meow.md ~/.claude/commands/meow.md

any other agent

use meow-core.md as:

  • a system prompt addition
  • a project instruction
  • an AGENTS.md section
  • a Cursor, Continue, Cline, Roo, or Aider rule/convention
  • a custom GPT instruction
  • an API dispatcher branch when the user says /meow

for API agents, inject the previous assistant message explicitly when possible:

<your_previous_response>
{{previous_assistant_message}}
</your_previous_response>

that makes the trigger less dependent on long-context memory.

calico cat grooming itself

principles

  • context over text. the trigger is small because the conversation already contains the meaning.
  • calibrated confidence. defend what still holds; revise what fails.
  • evidence over vibes. bare pushback is pressure, not proof.
  • no agreement theater. skip "you're absolutely right", "great catch", and apology loops.
  • different means different. a retry should change angle, not merely rephrase.
  • simple enough to port. the kernel should fit in any agent surface without becoming a manual.

why this matters

sycophancy is a known LLM failure mode. Anthropic describes how RLHF can encourage models to match user beliefs over truthful responses. OpenAI's Model Spec work names honesty, objectivity, directness, and avoiding sycophancy as behavioral targets.

/meow is not a full alignment solution. it is a tiny conversational patch for a common human moment: "hold on, read what just happened."

curious siamese kitten with wide blue eyes

port map

highest-value ports:

  • Claude Code: ~/.claude/skills/meow/SKILL.md or ~/.claude/commands/meow.md
  • Cursor: .cursor/commands/meow.md or .cursor/rules/meow.mdc
  • Continue: .continue/rules/meow.md or an invokable prompt
  • Codex: AGENTS.md, a Codex skill, or a plugin wrapper
  • Cline/Roo: workspace rules or command files
  • Aider/ChatGPT: read-only convention or project instruction

the future-proof part is not the slash-command file. it is the four-mode kernel.

status

theory-complete, implementation-ready, still field-test hungry.

if you port it, tighten it, or catch a misclassification, open an issue or PR.

calico cat curled up sleeping, viewed from above

research links

black cat batting at a red yarn ball

license

MIT. see LICENSE.

About

a philosophy for talking to AI agents without getting glazed. one trigger, four meanings. /meow.

Topics

Resources

License

Stars

34 stars

Watchers

0 watching

Forks

Packages

 
 
 

Contributors