Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/mifunedev/openharness/rlmnpx skills add mifunedev/openharness --skill rlmgit clone --depth 1 https://github.com/mifunedev/openharnessWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/mifunedev/openharness/rlm)<a href="https://agentmods.dev/skills/mifunedev/openharness/rlm"><img src="https://agentmods.dev/badge/skills/mifunedev/openharness/rlm.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00235 | $0.02584 |
| Opus 5 | $0.00118 | $0.01292 |
| Sonnet 5 | $0.00047 | $0.00517 |
| Haiku 4.5 | $0.00023 | $0.00258 |
Grade A, and why
rlm scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured today.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 174 lines — stays where its author put it; the contents beside it link to each section on GitHub.
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 | /spec execute |
each story re-reads disk = the REPL step — owned by the active implementation owner, never split into another session |
| Isolated recursion branches | .worktrees/ (the /worktrees skill) |
depth-2 sub-trees fork here — reused by reference, never edited |
| Recursion budget | /delegate (.oh/skills/delegate/SKILL.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 | scripts/query-context.mjs (US-004, this skill) |
partitions the artifact without ingesting it |
| Candidate selection | /weigh |
scores competing per-chunk answers |
Do not edit
/spec execute's task cycle or anything under.worktrees/./rlmis a consumer of both. The only genuinely new substrate this skill adds isquery-context.mjsand this procedure.
When to use
/rlm <artifact> "<query>"to answer a question over an artifact too large to read whole (a big log undercrons/.cron.log, a large corpus file, a whole directory).- As a sub-step of
/weighwhen the cohort being sampled spans a large artifact that must itself be decomposed before sampling.
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- today Changed dbd5e9ab4359
- 4d ago First seen · 174 lines · 235 tokens per session scan A 19cd4979dc51
rlm is a skill published in the GitHub repository mifunedev/openharness (36 stars, last pushed yesterday), licensed Apache-2.0. It adds 235 tokens to every session and 2,584 once invoked, about $0.0012 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
data-visualization
Use for creating publication-quality charts and multi-panel analysis summaries. Triggers when tasks involve visualizing data, plotting results, creating charts, or producing visual reports from analysis output.
cuml-machine-learning
Use for GPU-accelerated machine learning on tabular data using NVIDIA cuML. Triggers when tasks involve classification, regression, clustering, dimensionality reduction, or model training on datasets.
blog-post
Writes and structures long-form blog posts, creates tutorial outlines, and optimizes content for SEO with cover image generation. Use when the user asks to write a blog post, article, how-to guide, tutorial, technical writeup, thought leadership piece, or long-form content.
social-media
Drafts engaging social media posts, writes hooks, suggests hashtags, creates thread structures, and generates companion images. Use when the user asks to write a LinkedIn post, tweet, Twitter/X thread, social media caption, social post, or repurpose content for social platforms.
remember
Review the current conversation and capture valuable knowledge — best practices, coding conventions, architecture decisions, workflows, and user feedback — into persistent memory (AGENTS.md) or reusable skills. Use when the user says: (1) remember this, (2) save what we learned, (3) update memory, (4) capture…
textual-screenshot
Capture a Textual terminal UI as an SVG using its headless test harness. Use when asked to make, attach, or preview a screenshot of deepagents-code/dcode or another Textual app, visually verify a TUI state, or render a modal, screen, or widget without a desktop or browser.