meow — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited meow (Rules) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
<p align="center"> <img src="cats/animated/13-maneki-cat.svg" alt="lucky cat waving its paw" width="150"> </p>
<h1 align="center">meowmeow</h1>
<p align="center"> <em>one tiny trigger for better conversations with AI agents.</em><br> one word, four meanings. read the room, not the text. </p>
<p align="center">meow.</p>
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.
<p align="center"> <img src="cats/animated/17-peeking-cat.svg" alt="cat peeking over a fence with darting eyes" width="200"> </p>
/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.
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.
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.<p align="center"> <img src="cats/animated/12-formal-cat.svg" alt="cat sitting formally with a swishing tail" width="110"> </p>
current Claude Code supports user-invoked skills. install meow as a skill:
mkdir -p ~/.claude/skills/meow
cp meow.md ~/.claude/skills/meow/SKILL.mdthen type /meow.
legacy custom command layout:
mkdir -p ~/.claude/commands
cp meow.md ~/.claude/commands/meow.mduse meow-core.md as:
AGENTS.md section/meowfor 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.
<p align="center"> <img src="cats/animated/08-grooming-cat.svg" alt="calico cat grooming itself" width="140"> </p>
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."
<p align="center"> <img src="cats/animated/14-kitten.svg" alt="curious siamese kitten with wide blue eyes" width="130"> </p>
highest-value ports:
~/.claude/skills/meow/SKILL.md or ~/.claude/commands/meow.md.cursor/commands/meow.md or .cursor/rules/meow.mdc.continue/rules/meow.md or an invokable promptAGENTS.md, a Codex skill, or a plugin wrapperthe future-proof part is not the slash-command file. it is the four-mode kernel.
theory-complete, implementation-ready, still field-test hungry.
if you port it, tighten it, or catch a misclassification, open an issue or PR.
<p align="center"> <img src="cats/animated/15-curled-cat.svg" alt="calico cat curled up sleeping, viewed from above" width="170"> </p>
<p align="center"> <img src="cats/animated/03-yarn-cat.svg" alt="black cat batting at a red yarn ball" width="140"> </p>
MIT. see LICENSE.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.