rlm

# rlm — context-as-environment decomposition The **`/rlm`** skill is Layer B of the harness RLM integration (the plan: `.claude/plans/there-s-a-whole-snappy-crayon.md` § Layer B). It answers a query over an artifact too large to ingest by treating that artifact as an **environment the root agent addresses** — grep/slice/chunk-map — rather than a blob it reads into its context window. It then **recurses** sub-agent calls over the narrowed chunks under a bounded budget, and **aggregates** their structured returns, routing competing candidate answers through `/weigh`. **Single responsibility.** `/rlm` owns *decomposition*; `/weigh` owns *selection*. They compose: `/rlm` fans sub-calls out over chunks, `/weigh` scores/selects among the candidate answers a chunk yields. This skill never re-implements selection — it calls `/weigh`. **Reuse, don't reinvent (load-bearing).** The recursion substrate already exists: | Substrate | Owner | How `/rlm` uses it | |---|---|---| | Recursion **loop** | `.oh/scripts/ralph.sh` | each iteration re-reads disk = the REPL step — **reused by reference, never edited** | | Isolated recursion **branches** | `.oh/worktrees/` (the `/worktrees` skill) | depth-2 sub-trees fork here — **reused by reference, never edited** | | Recursion **budget** | `.oh/agents/advisor.md` | the `Max depth N / Max children per level M / Step budget S` triple — `references/recursion-budget.md` points at it and adds a per-run token ceiling | | Chunk-map **primitive** | `scr...