{
  "markdown": "---\ntype: Readme\ntitle: SDLC Migration\ndescription: Reusable TypeScript-native multi-project workspace on the SDLC + OKF standard, with LLM Wiki 2.0 memory and a test gate for everything that enters.\ntags: [workspace, sdlc, okf, readme, migration]\ntimestamp: 2026-07-02T00:00:00Z\n---\n\n# SDLC Migration\n\nA fresh, TypeScript-native, multi-project workspace built on the **SDLC + OKF + LLM Wiki 2.0**\nstandards, with a **Podman two-pod test gate** that proves any artifact - skill, tool, memory,\nharness, model switch - minimal, well-formed, efficient, and model-agnostic (`pass^5` across\nLLM families) **before** it is admitted. Use it to revamp a workspace onto the new standards,\nor to test before switching LLM, harness, or SDK.\n\n![SDLC Migration: the standard's six domain cartridges, the OKF format, the LLM Wiki 2.0 memory, the two test pods, and the prebuilt entry-gate tests](docs/assets/sdlc-migration-hero.png)\n\n## Author's note\n\nGoogle published the new SDLC and its agent whitepapers. Google Cloud published OKF, the\nknowledge format that maps to Karpathy's \"LLM Wiki\" idea (this workspace's OKF-native\nimplementation is what I call LLM Wiki 2.0). The skills standard spread across vendors at the\nsame time, and the published examples were blunt about harness size: Anthropic reported a\n150k-to-2k token reduction with skills, Vercel deleted 80% of its agent's tools.\n\nThese standards address more than size. They target the concerns that decide whether you own\nwhat you build: switching the LLM without losing quality, staying provider-agnostic instead of\nmarried to one vendor, and keeping your knowledge in an open, plain-text format that any tool\nand any model can read. Everything you invest into a workspace, the memories, the skills, the\nprocesses, stays yours and stays portable.\n\nI had spent over a year perfecting my VS Code setup, my memory system, the whole thing. Now\nthe standards, and even my API providers, were telling me to drop most of it.\n\nSo I tested it in a separate workspace first: 45% reduction in memory size and a 96% match\nrate across models, including different providers. That convinced me. Instead of patching my\nold setup, I built this workspace clean on the new standards, with an entry gate, so that\neverything I had, and everything future, migrates in the right way: classified, tested, proven\nmodel-agnostic, converted to the standard, then admitted.\n\nI am probably not the only one facing this. So here it is.\n\n## Origins and attribution\n\nI wrote the two PRDs, assembled published pieces (Google's SDLC and agents whitepaper corpus,\nthe Open Knowledge Format, Matt Pocock's skill chain), and use the result myself. The original\nwork here is the assembly: the distilled standard, the workspace substrate, and the entry gate.\nNaming note: `SDLC` is the publication repo name and \"SDLC Migration\" the project title;\n`000_sdlc_v1` (in the package name, container names, and internal docs) is the stable internal\nworkspace ID on the author's multi-workspace machine - same thing, different contexts.\nSources and attribution: [_foundation/PROVENANCE.md](_foundation/PROVENANCE.md); licensing and\nthird-party terms: [LICENSE](LICENSE).\n\n## Orientation\n\n| Where | What |\n|---|---|\n| [AGENTS.md](AGENTS.md) | The always-loaded core: identity, standing rules R1-R5, map. Read first. |\n| [wiki/](wiki/index.md) | The memory bundle (LLM Wiki 2.0): memories, cross-cutting asset index, archive. |\n| [sessions/](sessions/index.md) | Session records: log, chain-of-thought, handover per session. |\n| [projects/](projects/index.md) | Registry of projects hosted in this workspace. |\n| [docs/](docs/index.md) | Workspace docs: documentation method, agent seams, conflict log. |\n| [tools/](tools/) | Deterministic TypeScript scripts (`npm run start-session` etc.). |\n| [_foundation/](_foundation/README.md) | The original build handover bundle, kept verbatim: the standard (authority), OKF spec, skills, corpus. Historical instructions, not usage docs. |\n\n## Prerequisites\n\n- **Node.js ≥ 24** and git\n- **Podman** (rootless is fine) with a running machine - only needed for the gate's live path\n- **API keys** for the gate's proof gates: copy [.env.example](.env.example) to `.env` and fill\n  in `CASE_ANTHROPIC_API_KEY` and `GEMINI_API_KEY`. Everything except gates C/D and trajectories\n  works without keys (`--offline`).\n\n## Quickstart\n\n```\nnpm install                            # workspace-local toolchain, pinned\nnpm run typecheck && npm run selftest  # PRD1 smoke suite (sessions, memory, git step)\nnpm run gate -- selftest --offline     # gate pipeline, keyless and podman-less\nnpm run gate -- up                     # build + stand the two pods (idempotent)\nnpm run gate:selftest                  # full live suite: gates A-D cross-family (costs cents)\n```\n\nFirst time here? Follow the [first gate run tutorial](docs/tutorials/first-gate-run.md).\n\n## Usage\n\n```\nnpm run start-session   # list prior sessions (never reads their bodies)\nnpm run log-session     # scaffold the session record for the closing session\nnpm run gate -- run <artifact-dir>     # put an artifact through the entry gate\n```\n\nAgent-side, the session flows are the `/starting-session` and `/logging-session` skills. The\ngate's CLI reference is generated at [docs/reference/gate.md](docs/reference/gate.md); how-tos:\n[admit an artifact](docs/how-to/admit-an-artifact.md), [add a taxonomy class](docs/how-to/add-a-taxonomy-class.md).\n\n## Standard and provenance\n\nThe design authority is the standard shipped verbatim at\n[_foundation/standard/index.md](_foundation/standard/index.md). Sources and attribution for all\nvendored material: [_foundation/PROVENANCE.md](_foundation/PROVENANCE.md).\n",
  "bytes": 5698,
  "sha": "96087c907d411f53de645a6bade40313c12ba70ee2b498cb8d15c048083bd04d",
  "repo_slug": "war851/sdlc",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/okf_war851_sdlc_wiki_index_md_dfdb1e9a/readme"
}