/Upgrade

name: Upgrade
evals:
  deterministic:
    - command: "bun LIFEOS/TOOLS/UpdateModels.ts --check"
      falsifier: "exits nonzero when a Claude id is pinned outside the registry, agent frontmatter skips tier aliases, or a non-Claude versioned id outside CROSS_VENDOR sits in executable code"
  manual:
    reason: "recommendations require review that their cited technique is new, applicable, and not already adopted or rejected"
    falsifier: "the reviewer finds a recommendation lacks a supporting source, duplicates current state, or cannot map to a concrete improvement"
metadata:
  short-description: "Find actionable LifeOS improvements from harness releases, practitioner techniques, and internal reflections; filter already-adopted or rejected ideas."
version: 1.4.3
description: "Improve LifeOS from what the best practitioners are shipping around AI harnesses — Anthropic first (changelogs, docs, releases), then trusted creators, trending repos, and the system's own reflections — extracting concrete techniques and filtering them against verified current state so nothing already-done or rejected is re-recommended; also digests AI industry news and tracks AI competitors. USE WHEN upgrade, system upgrade, check Anthropic, new Claude features, algorithm upgrade, LifeOS upgrade, mine reflections, upgrade models, update models, latest models, are we on the latest models, model freshness, AI news, what's new in AI, AI industry news, smol.ai, AINews, Wes Roth, competitor tracking, what are OpenAI and Google doing. NOT FOR mining one piece of content (Harvest), releases or repo ops, or security news (SecurityUpdates)."

Upgrade

**Contents:** Ideal State · Intent Routing · Sources & Tools · Data & Config · Gotchas · Examples

Improves LifeOS from what the best practitioners are shipping around AI harnesses, Anthropic most importantly, and from the system's own reflections, as tiered, evidence-backed recommendations, and keeps every model LifeOS uses on its vendor's latest release. It also answers "what's new in AI" with a sourced news digest, a competitor report and an Anthropic updates digest scored for LifeOS impact (`Intents/NewsDigest.md`, which absorbed the retired AINews skill).

Signal comes from two directions, and a good run uses both: **external** (what Anthropic and the best practitioners are shipping) and **internal** (what the system's own reflections and failure history say is weak). The most valuable recommendations are usually where the two agree.

Ideal State

• Every recommendation shows the technique itself (quoted or code-blocked from its source), names the exact LifeOS file or component it improves, and carries a Prior Status backed by file:line evidence gathered in this run.
• Nothing already implemented, deferred by decision, or rejected is recommended again: implemented items appear under Skipped Content with their evidence, and an idea rejected in `MEMORY/KNOWLEDGE/REJECTED/` or the Upgrades store returns only with a named reason the context changed.
• No absence is reported that was not positively probed this run, and no adoption is recommended without a backward-compatibility check against current skills, hooks and workflows.
• A sweep report follows `References/OutputFormat.md` and arrives on its deadline, listing every source processed, skipped (with the reason) or timed out, so a missing lane lowers coverage without delaying or hiding it.
• A "what's new in AI" request returns one deduplicated, sourced digest saved under `MEMORY/RESEARCH/`, with any failed source named as unverified (`Intents/NewsDigest.md`).
• After a model run, no lane sits behind its vendor's latest same-class release unless the report lists it as a decision with its exact one-line fix.

Intent Routing

| Intent | Trigger | File | |----------|---------|------| | **Upgrade** | "check for upgrades", "check sources", "any updates", "check Anthropic", "check YouTube", "upgrade" | `Intents/Upgrade.md` | | **MineReflections** | "mine reflections", "check reflections", "what have we learned", "internal improvements", "reflection insights" | `Intents/MineReflections.md` | | **AlgorithmUpgrade** | "algorithm upgrade", "upgrade algorithm", "algorithm upgrade proposals" | `Intents/AlgorithmUpgrade.md` | | **ResearchUpgrade** | "research this upgrade", "deep dive on [feature]", "further research", "dig deeper" | `Intents/ResearchUpgrade.md` | | **Models** | "upgrade models", "update models", "model upgrade", "latest models", "are we on the latest models", "model freshness" | `Intents/Models.md` | | **FindSources** | "find upgrade sources", "find new sources", "discover channels", "expand monitoring" | `Intents/FindSources.md` | | **NewsDigest** | "what's new in AI", "AI news", "latest AI news", "smol.ai", "Wes Roth", "competitor tracking", "Anthropic updates", "Anthropic updates digest", "what changed at Anthropic and what do we need to do" | `Intents/NewsDigest.md` |

**Default intent:** a bare "upgrade" or "check for upgrades" runs **Upgrade** (which includes reflection mining). "Check Anthropic" is the Upgrade sweep's tiered recommendations; "Anthropic updates" is NewsDigest's ANTHROPIC UPDATES digest. Both read the same `Tools/Anthropic.ts` diff.

| File | Read when | |------|-----------| | `References/OutputFormat.md` | writing any report: section order, Prior Status legend, table columns, hard rules | | `References/ExampleReport.md` | checking a finished report against a worked example of the format | | `Setup.md` | first-time setup: optional GITHUB_TOKEN, YouTube channels, user sources and the programs those lanes call |

Sources & Tools

| Surface | Contract | |---------|----------| | Anthropic (30+ sources: blog, changelogs, GitHub repos, docs) | `bun Tools/Anthropic.ts` — diffs against `USER/CUSTOMIZATIONS/SKILLS/Upgrade/State/last-check.json`, updates it itself | | YouTube channels | Config: `youtube-channels.json` in CUSTOMIZATIONS (optional; create it as `{"channels": []}` if absen