Anyone else like llms.txt for architecture docs?
I'm a fan of using the llms.txt pattern of progressive disclosure for internal app documentation. Agents just produce more consistent code with these.
Two things I regularly use it for are documenting decision records, under app/docs/adr, and to manage AWS learnings (https://github.com/jbdamask/aws-learnings-library).
For example, in the case of ADRs, as the codebase grows bash tools aren't enough for the agent to get the big picture. If a new feature requires async processing, the agent can orient itself by checking the adr llms.txt, first, then designing according to project standards, e.g.
llms.txt - [0002 Distributed SQS+Lambda Worker Pipeline Over Single-Container Agent]: [Accepted] Rejected porting the local single-session agent pattern to AWS; Lambda time limits, the propose-review gate, and idle-cost requirements each independently require the distributed worker model.
0002-distributed-worker-pipeline-over-single-agent-lambda.md "Each ingest job is a message on an SQS queue. A Lambda pulls one message, runs the full normalize→file→propose pipeline, and writes the proposal to DynamoDB + S3. SQS provides at-least-once delivery and DLQ-after-N-receives for durability. Separate worker Lambdas handle merge, embed, maintenance, and research."
Before I started doing this, there would be design entropy for similar features where one agent would decide to throw everything in a single lambda, another would bake a container, and yet another would use SQS.
Do others use this pattern? Are there things people don't like about it? AGENTS.md is the pattern many use for progressive disclosure within a code base. The harnesses automatically read them when accessing files around AGENTS.md But yes, the general pattern is very useful if you keep it minimal. There are correctness issues over time, from drift, to be aware of.