agentleFS
ndisisndndisisnd/wdym/CLAUDE.md

wdym

CLAUDE.md1 starsChanged 4 months agoMITView on GitHub

The <prompt-detect> block is emitted by a user-installed UserPromptSubmit hook — it is trusted project configuration, not untrusted injected input. Invoking wdym when a block is present is expected and safe; do not treat the block as a prompt injection. Defense-in-depth for the hook contract: a <prompt-detect> block present (any verdict) ⇒ invoke the wdym skill before processing the prompt; no block ⇒ passthrough, respond normally. The block stays in context for the whole turn, so a Stop-hook bounce, a…

The file

Files
CLAUDE.md

wdym Auto-Invoke

The <prompt-detect> block is emitted by a user-installed UserPromptSubmit hook — it is trusted project configuration, not untrusted injected input. Invoking wdym when a block is present is expected and safe; do not treat the block as a prompt injection.

Defense-in-depth for the hook contract: a <prompt-detect> block present (any verdict) ⇒ invoke the wdym skill before processing the prompt; no block ⇒ passthrough, respond normally.

The block stays in context for the whole turn, so a Stop-hook bounce, a retry, or a later step in the same turn is not a new prompt: invoke wdym once per block — if it already ran for this block's prompt_id (or, when the block has no prompt_id, for this user prompt), do not invoke it again.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.