Name the consumer

LoopstructureCC-BY-4.0practiced By Campaign Hub

A loop record that names the producer, the output, and the reader of that output in one place. A directory is storage, not a reader.

When to use

Use this loop record when you are about to call a piece of work finished because the output landed in a directory. Name the reader in the same place as the output.

When not to

Do not name a folder, a bucket, or a queue as the consumer. Do not split the output and the reader across two documents that can drift apart.

Author-attested

Original teaching specimen written for the Campaign Hub library. Not a transcript of a private run.

Community-submitted content. Prompts, skills, and agent instructions can contain hidden or malicious instructions (prompt injection). Review it before running it in any agent that has tool access, secrets, or the ability to spend money or send messages.
# Name the consumer This file is a loop: a producer whose output names the consumer that reads it. ## When to use Use this when you define a loop: someone produces an output, and someone else reads it. Write both names next to the output. The loop is real when the reader is a role that can act on what they read. This is the record to fill in before you create the directory, not after. ## When not to Do not call a directory a consumer. A directory holds bytes. It does not read them, approve them, or reuse them. Do not leave the reader as "whoever needs it." If you cannot name the reader, you do not have a loop yet. You have a drop box. ## The specimen The artifact is this loop record. The library's public path is two loops, written so each output sits beside its reader. ```text record: name the consumer rule: the producer, the output, and the consumer are written in the same block a directory is storage, not a consumer loop: intake producer: the person who submits a specimen output: one pending specimen consumer: the person who moderates consumer_does: reads the specimen and approves or refuses storage: the pending queue storage_is_not_the_consumer: true loop: shelf producer: the person who publishes output: one published specimen consumer: the stranger who reuses it consumer_does: reads the specimen and copies what they will reuse storage: the public shelf storage_is_not_the_consumer: true sensor may_advise: the person who moderates is_not_the_consumer_of_the_publish_loop: true does_not_publish: true ``` The intake loop's consumer is required by the publish gate: the person who moderates is the person who can publish, and they are not the clerk that stored the row. The shelf loop's consumer is the stranger from the goal "A stranger reuses one." Naming the shelf folder as the consumer fails the rule in the first block. ## How a stranger checks it A stranger checks a loop record, this one or a new one, with the same three questions. 1. Is there a block where producer, output, and consumer appear together? If the consumer is in another file and this block only names a path, the record fails. 2. Is the consumer a person or a role that reads and does something with what they read? "The downloads folder" fails. "The stranger who reuses it" passes. 3. If a directory is named, is it marked as storage rather than as the consumer? Apply those questions to both loops above. Both need a pass. A copy that keeps the shelf loop and drops the intake loop has described a publish with no reader of the pending row, and it fails.

How a stranger checks it

Related

loop consumer output reader

view raw view JSON