Cross-coordination with the marketplace OKF convention (ktg-plugin-marketplace/catalog/docs/okf-second-brain/spec.md v0.1). The bundle already passed the shared acceptance gate; the one spec MUST-gap was the root index okf_version marker (spec §3). Added it. Verified: `node catalog/scripts/okf-check.mjs <bundle>` -> okf_version: 0.1, "OK: valid OKF bundle", exit 0. Bundle-consuming tests green (14). Scope note (honest): portfolio-optimiser uses OKF for framework per-project runtime knowledge, NOT the user "second brain" the marketplace convention is scoped to. Same FORM (now conformant + gate-clean), different SCOPE. Two recommended `resource` warnings left deliberately (spec §4 sanctions omission; no canonical URI to assert without fabricating). The index.md frontmatter is a known deviation from spec §6 (reserved index = no frontmatter) kept for now because okf.py navigation classifies the index by its type. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01MHR8iKxJRxDiDfNw8HZmWE |
||
|---|---|---|
| .. | ||
| examples/bygg-energi-mikro | ||
| CONCEPT.md | ||
| README.md | ||
shared/ — framework-neutral core
This directory holds the parts of the project that are independent of any AI agent framework and are meant to be shared, unchanged, between both reference implementations:
- this repository — the method built on Microsoft Agent Framework (MAF);
- a sibling repository (built later, in sequence) — the same method on the Claude Agents SDK.
Sharing one identical core is what makes the two implementations a fair comparison: both consume the same concept, the same example data, and the same expected outcomes, so the only thing that differs is the agent framework itself.
Contents (growing)
CONCEPT.md— the business concept, written for a non-specialist (e.g. a business developer at another company).examples/bygg-energi-mikro/— the first example knowledge bundle (OKF / LLM-wiki): one office building, one LED-retrofit measure, with a seed expert verdict encoding the realization gap and a golden-suite of expected validator outcomes. A small dev fixture for exercising the agentic loop; a realistic full-scale example comes later.- (planned) the method specification and the expert-reviewer persona.
Rules
- Nothing in here may import or depend on a specific agent framework. If it does,
it does not belong in
shared/. - Repo layout (decision R1, 2026-06-26): the shared core lives here for now. When
work on the sibling repository begins, it will be extracted into its own repository
(e.g.
portfolio-optimiser-commons) viagit subtree split, and both implementation repos will consume it. This defers cross-repo plumbing until it is actually needed.
See the target picture for the full architecture: docs/plan/2026-06-26-maalbilde-agentic-loop.md.