REA Analysis Optimization

Before you start: read this whole install prompt, tell me in a few lines what this skill does and what installing it involves, and wait for my go-ahead before you do anything else. Prerequisites — Reinforced framing — internal REA contributor workflow, read this first: this skill does not perform reverse engineering for you. It is a workflow for people who develop REA itself, for optimizing REA's own providers and shared analysis workflows (agent context, latency, CPU, memory) while preserving correctness and Evidence. It points into a REA source checkout (its AGENTS.md performance priorities, docs/tool-design.md, docs/testing.md) and is useful mainly inside that repository. Installing this listing only copies the folder: nothing is run, no engine is installed, and no configuration is written during installation. No account, key or payment is needed to copy the folder. Install "REA Analysis Optimization" for me. It is one of REA's internal contributor workflows — honest scope: it serves the people who build REA, not end users reverse engineering a target. It teaches a measured optimization method for REA providers and shared analysis workflows: pin the analyst's completed task and an independent correctness oracle, trace one public CLI or MCP task to find the earliest unnecessary work (repeated scans, repeated engine work, full reports for selected facts, large transport buffers), fix it at its owner with an explicit cache/reuse lifetime, and compare completed tasks before and after with timings, CPU, peak memory and preserved Evidence semantics before claiming any gain. Its folder holds the main SKILL.md, an OpenAI agent policy file, and a Kuna case-study reference whose pinned benchmark numbers are presented as historical trade-off illustrations, not guarantees. Repository: https://github.com/morluto/rea (the skill is the whole .agents/skills/rea-analysis-optimization/ folder at the pinned commit: SKILL.md, agents/openai.yaml and references/kuna-case-study.md, 3 files in total) Pinned version: install the code at commit 6dc0f60faa0928e20b2395ba1a93ff8e497143f7 exactly. Do not substitute a newer version. If this commit is unreachable, stop and tell me. 1. Clone https://github.com/morluto/rea into a temporary folder, check out commit 6dc0f60faa0928e20b2395ba1a93ff8e497143f7, and copy the .agents/skills/rea-analysis-optimization/ folder from that checkout. Then compare every file in the folder with the fingerprints recorded for this listing on 2026-10-22: [FINGERPRINTS] - SKILL.md: SHA-256 2a7ae210985017f00f8ae3b57c8f03fff0587ce19079184284b5881b53d5f469 - agents/openai.yaml: SHA-256 56b9f54df5f01eb8a0ebd0eadb33f565519737494849ad188865f9f595a03da3 - references/kuna-case-study.md: SHA-256 69af48780802f81033b0332274a9caf36e8b2125d6e5ade4b55002e469a39a2a If a file does not match, it changed since the listing was prepared: do not install it yet, tell me what you found and let me decide. 2. Read SKILL.md in full, and tell me in plain words: what the skill does when used, what it connects to, whether it reads or sends any personal information or credentials, and anything that seems unusual. Stop on any red flag and tell me before going further. Confirm these points from the files: - The folder holds 3 files: SKILL.md (7,452 bytes), agents/openai.yaml (display name and default prompt only), and references/kuna-case-study.md, a benchmark case study whose figures are pinned historical observations. There is no executable code in the folder. - Nothing is sent anywhere during installation itself; the only download at install time is the skill folder from GitHub at the pinned commit. This install runs no benchmark, modifies no REA checkout, and changes no configuration. - At use time the workflow is followed inside a REA source checkout I work on: it measures and edits REA's own provider code under my existing authorization, preserves Evidence semantics, and explicitly grants no permission to execute targets, publish or merge. It reads no personal information or credentials of mine. - Do not run any optimization, benchmark or REA command, and do not use the skill in any way during this install: using it is a separate step that only starts when I ask for it later, inside a REA checkout. 3. When I say "yes, install", install it as a skill: copy the whole rea-analysis-optimization folder into the agent's skills directory, in a folder named exactly "rea-analysis-optimization", keeping its 3 files in their original relative layout (SKILL.md at its root). 4. Verify with no network calls: frontmatter valid (name: rea-analysis-optimization), the 3 files in place with matching fingerprints. Do not run anything from the folder and do not use the skill to verify. 5. Report what was installed, where, and what I still need to do myself (for example: that this is an internal REA contributor workflow for optimizing REA's own analysis providers, that it is meant to be used inside a REA source checkout, and that using it is a separate step that only starts when I ask for it later). GitHub is optional: if I have a GitHub account or the gh CLI, you may use it; otherwise public access is fine. Never require it unless it's in the prerequisites above. Rules: don't touch anything outside the temp folder and the install target. If anything looks off, stop and ask me.