configure-rag-rat-dream skillA
This file is byte-identical to the first copy the registry indexed. Same content hash, same audit grade.
configure-rag-rat-dream is agent-read markdown (skill) from cq27-dev/rag-rat: Use to enable and operate rag-rat's optional AI memory-maintenance passes — the `dream --verify` / `--compact` model turns that verify repo memories (flag claims that no longer hold) and compact them (shorter summaries). Off by default. This configures `[llm.dream]` / `[llm.dream.remote]` (a chat model, over a Connect endpoint or an ephemeral Modal/RunPod cookbook box — vllm/ollama, never infinity), and sets up running it on demand or on a schedule (systemd timer). Pairs with the `dream-review` .
Indexed from public GitHub and served as immutable, content-addressed versions. Install it pinned to an exact SHA-256 with the mdr CLI, and every file is verified against the hash recorded here before it reaches your agent. The deterministic audit below grades the latest version, and the same file always earns the same grade.
What the file says
# configure-rag-rat-dream — enable and run the AI memory-maintenance passes rag-rat's `dream` command has an optional **model turn**: the `--verify` / `--compact` passes that AI-verify repo **memories** (flag those whose claims no longer hold → `memory_reality`) and compact them (shorter drive-by summaries). It is rag-rat's **only** generative-model dependency, **off by default**, and gated by a deterministic layer — `rag-rat dream` stays 100% deterministic unless `[llm.dream] enabled = true` and you pass `--verify`/`--compact`. It earns its keep only once a repo has **accumulated memories**, so this is a later, deliberate setup, not something to do at first index. The `dream-review` skill triages the findings these passes produce — run this skill to turn the model on, that one to work through what it surfaces. ## When to set it up - rag-rat has been in use a while and memories have accumulated. - The user wants AI **verify** (reality-check memories) and/or **compact** (shorter summaries). Otherwise skip it — the deterministic `dream` is enough. ## Config — mirrors `[llm.embedding.remote]`, but a CHAT backend …
Read the whole file at its exact version.
How to install
mdr add cq27-dev/rag-rat/configure-rag-rat-dream@git:20260711.a2328dcmdr add cq27-dev/rag-rat/configure-rag-rat-dream@sha256:1d18a1c2ad4b45eaPin to a label to follow the author's releases, or to a sha256 to freeze the exact bytes forever. Either way the resolved hash is written to mdr.lock, and mdr install reproduces it on any machine.
[](https://markdownregistry.com/a/art_cps4iknpizm2xugj)
1 badge views in 30 days
Versions
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (6049 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
cq27-dev/rag-rat · 20 stars · license MIT · pushed 2026-09-23 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_cps4iknpizm2xugj GET https://markdownregistry.com/api/v1/resolve?ref=cq27-dev/rag-rat/configure-rag-rat-dream GET https://markdownregistry.com/api/v1/blob/1d18a1c2ad4b45eaeebbbab6c9008882f362e393fc78063a8d78b679a9d54b4f
Your agent does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
More from cq27-dev/rag-rat
Every file in cq27-dev/rag-rat