Upgrade

Customization

Before executing, check for user customizations at: ~/.claude/LIFEOS/USER/CUSTOMIZATIONS/SKILLS/Upgrade/

If this directory exists, load and apply any PREFERENCES.md, configurations, or resources found there. These override default behavior. If the directory does not exist, proceed with skill defaults.

🚨 MANDATORY: Voice Notification (REQUIRED BEFORE ANY ACTION)

You MUST send this notification BEFORE doing anything else when this skill is invoked.

1. Send voice notification:

   bashCopy code
   curl -s -X POST http://localhost:31337/notify \
     -H "Content-Type: application/json" \
     -d '{"message": "Running the WORKFLOWNAME workflow in the Upgrade skill to ACTION"}' \
     > /dev/null 2>&1 &
   

2. Output text notification:

   Copy code
   Running the **WorkflowName** workflow in the **Upgrade** skill to ACTION...
   

Upgrade

The ideal state: the system knows what the best people on the internet are saying, doing, and implementing around AI harnesses — Anthropic most importantly — and its configuration improves from that input. A run is done when every worthwhile new technique from the monitored sources has been extracted (quoted, mapped to a specific LifeOS file or component), every candidate has been checked against what the system already has or already decided, and the result reaches the user as tiered, evidence-backed recommendations they can act on immediately.

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.

Workflow Routing

Default workflow: a bare "upgrade" or "check for upgrades" runs Upgrade (which includes reflection mining).

The Contract (what every recommendation must satisfy)

1. Grounded in current state. No recommendation without a Prior Status tag (🆕/🔶/💬/🚫) backed by file:line evidence gathered this run. Already-implemented items go to Skipped Content with evidence — that's the proof the prior-state check ran. Rejected ideas (MEMORY/KNOWLEDGE/REJECTED/) only resurface with a named reason the context changed. This standard binds internal synthesis inference exactly as it binds external findings: before any absence-claim earns a 🆕/CRITICAL tag, the thing claimed missing must be positively probed this run (grep/read for it), never inferred. A reported absence you did not check is a fabricated finding — the 2026-08-06 scan shipped a false CRITICAL across seven skills by grepping context: fork while never grepping background:. Internal inference is exempt from nothing.
2. A technique, not a pointer. Quote or code-block the actual content; name the exact LifeOS file or component it improves; include What It Is and How It Helps LifeOS (≤2 concrete sentences each). The test: if "show me the technique" has no answer, it doesn't ship. Content with nothing extractable goes to Skipped with a reason — skip boldly rather than dilute.
3. Won't break what exists. Check backward compatibility against current skills, hooks, and workflows before recommending adoption.
4. Formatted per the contract. References/OutputFormat.md is the single source of truth for section order, Prior Status legend, table columns, and hard rules.

Sources & Tools

Source labels in output: GitHub: claude-code vX.Y.Z · YouTube: Creator @ MM:SS · Docs: Section · Blog: Title.

Gotchas

• Hard deadline, fail-open — never block on a straggler. Set a synthesis deadline (~4 min) at dispatch; report with whatever is back when it hits. A missing source is listed as ⏳ timed out in Sources Processed; it degrades coverage, never delays the report. (2026-07-18: one hung GitHub-trending agent stalled a run ~1 hour.)
• Right-size the fan-out (~8 agents). Small-file reads collapse into one agent; network sources get short budgets and are first to drop. Over-fan-out is the failure the reflection corpus flags most.
• Budget the claude-code-guide freshness spawn per-spawn — it dies on a broad ask. Asking one spawn to cover the whole Claude Code surface (hook events, settings.json, slash commands, SKILL/subagent frontmatter, MCP, SDK, API) returns nothing: it fans out a batch of doc lookups on its first turn and the combined results blow its context window, surfacing as Prompt is too long ~10s after spawn. The prompt length is not the cause — a trivial prompt to the same agent type in a larger parent conversation completes fine; how much the ask makes it FETCH is the variable. Cap at ~3 areas per spawn, tell it to look things up rather than pull whole pages, and split the surface across parallel spawns so losing one costs a slice instead of the whole freshness check. Diagnostic tell: sibling agents in the same batch all succeed while this one dies — that points at the spawn's context budget, not the batch. Fallback that needs no agent at all: read Claude Code CHANGELOG from sources.json directly and diff the version range. (public PR #1659, @elhoim.)
• Idle teammate ≠ delivered result. Spawned agents sometimes go idle without sending output — a one-line SendMessage nudge recovers them. Nudge once; don't re-spawn.
• GitHub search 422s on bare OR between qualifiers with no free-text term. Give every query a free-text term; don't retry a 422 inside the budget.
• Absence from settings.json ≠ a dead hook. It's GENERATED by MergeSettings; hooks also fire via dispatchers (PreToolGuard) and Pulse HTTP. Flag "verify before concluding dark," never assert dead from absence.
• Check sources in parallel, not sequentially — the run is network-bound.

Execution Log

After completing any workflow, append a single JSONL entry:

bashCopy code
echo '{"ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'","skill":"Upgrade","workflow":"WORKFLOW_USED","input":"8_WORD_SUMMARY","status":"ok|error","duration_s":SECONDS}' >> ~/.claude/LIFEOS/MEMORY/SKILLS/execution.jsonl

Replace WORKFLOW_USED with the workflow executed, 8_WORD_SUMMARY with a brief input description, and SECONDS with approximate wall-clock time. Log status: "error" if the workflow failed.