POWER CLAUDE · SHIP WHILE YOU SLEEP · ~$105/MO NET VS MAX
Power Claude: The session died. The job didn't.
Start a Power Claude session, close the laptop, come back to a finished run — not a frozen chat.
What Power Claude adds Tired of losing work when a task never quite finishes? Health Check recovers stalled sessions in ~60s.
- Tired of losing work when a task never quite finishes? Health Check recovers stalled sessions in ~60s.
- Stop re-explaining the same job next session — Continuity rewakes unfinished work instead of skipping it.
- See the whole agent run as a live flow chart — every step, branch, and stall on one graph.
- Unmatched granular profile, session, and workflow insight so you know exactly where tokens go.
- Smart Token Saver trims excess noise without code-quality regression — more room for real work.
- Opt-in Auto-Rotation Engine (off by default) keeps long jobs shipping through rate limits on seats you own.
- Session Recovery pulls work back when Claude's context collapses — the run doesn't die with the window.
- Checkpoints name rewinds Claude can't — go back to a known-good state without guessing.
- Auto-nudge only on the trivial stops so agents keep moving without babysitting every prompt.
- Pre-commit review and session trails catch incomplete work before it ships as a bug.
- Model tabs keep Claude, Codex, Grok, and Kimi sessions apart.
- Multi-host isolation keeps Claude / Grok / Codex / Kimi seats from clobbering each other's state.
- Watchdog catches crashes before you notice; the status bar shows which seat is driving now.
- Token Tree + trip odometer show burn rate before you hit the wall — plan capacity, not panic.
Premium Trial: $0 today (card on file, then $12/mo) — or 7 days free, no card. Start shipping and stop overpaying — never look back.
Everything below is Claude-Code-specific. The engine every Power Agent ships with lives on the home page.
Session recovery, Token Saver, watchdog, auto-resume, dashboards, analytics, flow explorer, messaging, account groups — the full catalog with screenshots is on the Neural-LLM home page. This page covers what only Power Claude adds on top: Claude account rotation and the Max-vs-Pro seat math, Claude Core lockout visibility, checkpoints, session trail, and the optional patches to the official Claude Code extension.
Jump to: Balanced Mode · Token Saver · Watchdog · Session Recovery · Dashboard · Analytics · Flow Explorer · Messaging · CLI
Shared engine on the home page · Claude extras here
Built to make the six worst Claude Code failure modes disappear.
Your 5-hour quota runs out before your agent does.
When a seat hits its 5-hour wall the session pauses, names the reset time, and resumes on the same profile — no dead spinner. Switch on the opt-in Auto-Rotation Engine and the next prompt continues on a fresh seat you own: N seats, N independent 5-hour windows.
Once rotation is on, pick the policy that fits the work: Balanced to spread load evenly, Burst to drain one account fast when you're sprinting, Single to pin to one. Five Pro seats ≈ $83/mo — less than half the cost of Claude Max ($200/mo), same ceiling, no timer to stare at.
The quota wall is the most-upvoted Claude Code complaint of 2026 — and a rate-limited turn burns the tokens it never got to use. [GH #11810]
You're paying for Opus. Claude's routing you to Haiku. Would you even know?
Per-turn Model Attribution shows you exactly which model answered every single turn — so a silent downgrade to Haiku surfaces the instant it happens, not three bad outputs later. You see the swap in real time and can act on it: re-run it, escalate, or switch accounts — instead of paying premium prices for commodity output and never knowing.
The downgrade is real and undisclosed by default. External telemetry put ~36% of Claude Code subagent traffic on Haiku — roughly 20× cheaper than Opus, returned with no native indicator at all. One developer's words: "Silently gaslighting us to believe everything's normal."
[mirin.pro — "36% of Your Claude Code Subagents Are Running on Haiku"]
Auto-compact ate your context. The agent is guessing now.
The Watchdog snapshots your full session the instant before auto-compact fires — preserved as an immutable git ref you can restore with one click. When you resume, the agent works from the real decision chain, not a summary of a summary of a summary.
Resume Session replays the un-compacted context into the next turn, so the model knows precisely what the prior turns meant — the constraints that still apply and the ones that don't. No more silent context decay mid-refactor, no more hallucinated requirements after the third compaction.
Four hours of work. Lost. Because the session crashed.
Every session is persisted as JSONL plus an immutable git ref the moment work begins — so a crash, an OOM kill, or a reboot can't take your work with it. Your todos, tool calls, file edits, and full decision chain stay recoverable, and one click drops you back at the exact pre-crash state.
Because the snapshots are git objects, the history is tamper-evident and queryable with the tools you already use — not a fragile cache that "Claude Code Lost My 4-Hour Session" headlines are made of. One reported crash bug (#30700) stemmed from session storage that was never created, so nothing ever persisted. Power Claude's writes happen up front, every time.
The API bill was $47k. The job ran overnight with no warning.
The LLM Usage Dashboard shows live $/session, per-account token tracking, and a cache-read vs output breakdown as the work runs — plus plan-tier-aware hard-cap alerts that fire BEFORE your quota dies, not after the invoice lands. You see the wall coming with room to stop.
It catches what most dashboards miss: over 90% of the tokens in a Claude Code session are cache reads — invisible to naive trackers, still billing. Power Claude surfaces them and ties spend to the account and turn that incurred it, so an overnight run can't quietly become a four- or five-figure surprise. [DeSight — $47k invoice case]
You own five Claude accounts. You're only ever using one.
Power Claude runs all your accounts as one coordinated fleet — named once, rotated when you opt in. No logging out, no pasting the thread into a fresh login, no friction tax every time you hit a wall. The other four accounts finally do work instead of sitting idle.
That's the whole difference between owning five accounts and actually getting five accounts' worth of throughput. Five Pro accounts ≈ $83/mo, roughly half the cost of Claude Max ($200/mo) — same ceiling, ~$117/mo less in seat cost (the Power Claude licence is extra). Balanced / Burst / Single rotation policies, a VS Code & Cursor sidebar, and a pc CLI, all local — Power Claude never sees your prompts, and your accounts stay on your machine.
Your agent should keep working after you close the laptop.
Power Claude runs your accounts as a coordinated fleet — watchdog and session recovery as a single layer beneath Claude Code, with multi-account tools for seats you own. Official mode pauses on usage limits; optional Auto-Rotation is available when you opt in.
The alternative costs more than people realize. Logging out, logging back in, rebuilding context after every rate limit: a minute and a full context switch each time. Multiply that across a day of agentic sessions and it's hours that should have been output. Power Claude handles the recovery work: session recovery, watchdog auto-resume, and multi-account routing tools — polished VS Code + CLI product, your accounts never leaving your machine.
14-day Premium Trial (card on file), or 7 days free with no card. If Power Claude doesn't hand back real time in the first week, our team will get you dialed in — or you leave: cancel the Premium Trial before day 14 and nothing is charged; the no-card trial just lapses.
Leave it running. Come back to a finished task.
Every "Should I continue?" prompt and every hard stop that needs a human at the keyboard steals hours from agentic work. Your agent isn't stuck because the work is done — it's stuck because the tooling needed a babysitter. Across a day of sessions, that's idle time you didn't notice until you returned.
Silent throttles add a second layer. Anthropic may downgrade sessions to Haiku without a clear badge — slower, cheaper output quietly standing in for your intended model. Power Claude detects the downgrade per turn and surfaces it before it degrades your work.
Power Claude removes the babysitting classes that matter: auto-nudge clears trivial stops, watchdog detects stalls and crashes, and same-profile auto-resume keeps continuity on the seat that started the job. Optional Auto-Rotation Engine (off by default, opt-in with risk notice) can coordinate additional seats you own. Come back to progress, not a stalled prompt.
Community savings
$3,816,038 saved and counting*
Estimated savings across Power Claude users who run multiple Claude Pro seats they own instead of stacking Max plans — derived from our public cross-store install count.
How we calculate this
- Active users are estimated at 40% of our public cross-store download count — deliberately conservative; most installs are trials or second machines.
- Each active user is assumed to otherwise need one Claude Max 20× seat ($200/mo) to match the throughput of the Pro seats they own — the same basis as the per-user figure quoted across the site.
- What they run instead: five Claude Pro seats they own ($83/mo total) plus Power Claude Pro ($12/mo) — so one user's estimated saving is $105/mo.
- The cumulative figure integrates a linear adoption ramp from 2026-05-01 to today — early months count for less, not full weight.
- This is an estimate derived from public install counts, not a measured total. Once opt-in usage telemetry reaches a meaningful threshold, this counter switches to tracked, real figures.
Read the full cost breakdown: Claude Max vs pooled Pro accounts
*Estimate from public install counts — see "How we calculate this". Switches to tracked figures once opt-in telemetry clears its threshold.
CLAUDE CODE SEAT · ROTATION ENGINE
Power Claude features
Power Claude keeps your Claude Code seat working — Balanced Mode across the accounts you already own, the rotation engine, watchdog, Token Saver and dashboards. The same engine ships as Power Codex, Power Grok and Power Kimi, one license per host.
Why five Pro accounts beat one Max plan — and how Power Claude makes that usable.
The money math most people miss: Anthropic’s Claude Max 20× is about $200/mo for a single high-cap seat. Five legitimate Claude Pro seats (about $16.66/mo each on annual billing) total about $83/mo — so you keep roughly the same 5-hour session capacity class for $117+/mo less in seat cost than Max (the $12 tool is extra). Or keep spending ~$200 and run more Pro seats for ~2.5× the pool instead of one Max login.
Why that works: Max’s premium is mostly a higher ceiling on one account. Five Pro profiles each carry their own session budget; pooled capacity ≈ one Max 20× session class without paying Max’s single-seat markup.
What Power Claude does: it manages seats you already own (profiles + config dirs) so you see health, pick the right seat before work, and keep each session on its originating profile by default — no silent account hopping. When a seat hits a limit, Power Claude pauses and tells you (wait, switch plan, or API mode). Optional Auto-Rotation Engine (off by default; explicit opt-in with grey-area warning) can continue across seats you own after you turn it on — never a silent install default. The warning says the plain thing: rotating among accounts you already own is what the feature does, Neural-LLM does not represent that any particular use of it is permitted under Anthropic’s terms, and confirming that is yours to do — which is why it is off until you turn it on. The FAQ and the Acceptable Use Policy set out the rest.
$200/mo Max vs ~$83/mo five Pro · $117+/mo less in seat cost · seats you own
Model tabs: keep Claude, Codex, Grok, and Kimi sessions apart in one sidebar.
The sidebar scopes Home, sessions, usage, and settings by host family, auto-discovers the seats and API keys on your machine, and lets you pin or hide hosts. Running another host's seats needs that host's Power product — one license per host.
Model tabs · auto-discover · pin or hide · one license per host
Drain seats about to reset — leave nothing on the table.
When multi-account rotation is selecting among seats you own, Reset burn-down prefers accounts near a 5h or 7d usage-window reset that still have residual capacity — so quota is not left unused when the window rolls. Urgency ramps over the remaining window (steepest near reset). Far-from-reset seats stay available for later work.
Defaults: powerClaude.proxy.resetBurnDown = true; pairs with parallelMode = smart. This is usage-window reset (Anthropic rate-limit headers), not subscription billing renewal. Does not invent capacity or force auth-dead seats. Reset burn-down how-to · pairs with Runout Forecaster.
default ON · near-reset residual first · 5h + 7d · smart parallel
Claude's /rewind has a blind spot. Power Claude names it.
Claude Code's built-in /rewind only tracks files Claude edited through its own tools — it can't restore anything a bash command, a build step, a hand-edit, or another session changed, and it won't warn you. Power Claude reads both checkpoint layers — Claude's native /rewind history and its own durable, bash-inclusive session snapshot ref — and computes the bash-gap: the exact files that changed this session that /rewind would silently fail to restore. Power Claude's snapshot can. Today it runs on the command line: pc session checkpoints <id> and pc session bash-gap <id>. Checkpoints how-to · Help hub.
L0 native /rewind + L1 durable snapshot · bash-gap = changed − tool-edited · CLI: pc session checkpoints / bash-gap
See which AI session edited each line of code.
Session Trail adds a ⚡ icon in the editor gutter for every AI-edited line, plus CodeLens ("⚡ N sessions · last X ago") above functions. Hover any marked line and the popup shows the contributing session ID, model, and diff hunk. Click to open the session in the Sessions tab. The Edit History side panel lists every session that has touched the active file, sortable by model. Pre-Commit Review pulls all of this together at commit time, so reviewers see the complete AI decision chain before push — not after a bug report.
Gutter ⚡ icons · CodeLens · hover cards · per-file history · pre-commit review
Tells you when to upgrade — and when Anthropic downgraded you.
Power Claude can surface local recommendations from your own logs (for example plan options when limits are frequent). Throttled so you are not nagged. Recommendations are computed locally — zero telemetry leaves your machine unless you opt in. Your session data stays yours.
local-only computation · weekly throttle · opt-in telemetry only
CLAUDE CORE
Always know why your session is paused — and trust it to come back
When your whole profile list is rate-limited, Claude Code shows nothing but a spinner — you can't tell paused from hung. Power Claude surfaces the real reason and the soonest recovery time, then keeps its existing promise: the session resumes itself the moment a window clears, even hours later. Visibility plus unattended recovery, no babysitting.
Know exactly why your session is paused — and trust it to resume itself.
When every Claude account in your pool is rate-limited at once, Power Claude doesn't give up: its proxy keeps each session's retry loop alive (short synthetic-429 waits) so a session auto-resumes the instant a window clears. The problem was that Claude Code only showed its generic "thinking" spinner — no reason, no ETA — so a paused session looked exactly like a hung one. Power Claude now surfaces the real state in one consistent line across four surfaces: a VS Code status-bar banner, the Claude Code statusline, a one-time onset toast, and pc status — reading, for example, All Claude accounts rate-limited · auto-resume ~32m (22:30). It names the actual condition and the soonest reset across the pool, then clears itself automatically when an account frees up. And it pairs with what Power Claude already does: it resumes the session on its own, even hours later — even when the long 5-hour or weekly window won't clear for hours, you walk away and it picks the work back up the instant the window opens.
one message on 4 surfaces (status-bar banner / statusline / onset toast / pc status) · names the condition + soonest pool reset · auto-clears on recovery · resumes itself even hours later when the 5h/weekly window opens — no babysitting
OPTIONAL · REQUIRES THE OFFICIAL CLAUDE CODE EXTENSION
Enhancements to the official Claude Code extension
Optional. These patches augment the extension Anthropic ships — toggle each off in settings, or remove them anytime, and keep using Power Claude.
Everything in this section is optional. These are surgical patches applied directly to the Claude Code VS Code extension you already have installed — not separate tools. Power Claude fixes the rough edges Anthropic hasn't shipped yet: stops Claude Code stealing your cursor, pins your original request to every session, stamps each message with the time it was sent, badges your session list so it's readable at a glance. Every patch is reversible and self-heals across Claude Code auto-updates. Turn any single one off, or uninstall Power Claude entirely, and the editor returns to stock — the core of Power Claude (session orchestration, the savings, and auto-resume) works fully without any of them.
Your open file is not Claude's business — until you say so.
By default, Claude Code attaches whatever file you have open to every prompt. That means a prompt about your build script silently ships the API key in .env you happen to have open in the next tab, and a question about a CSS class drags in a 3,000-line component — roughly 30k tokens — you weren't even asking about, re-sent on every turn. Across one focused Opus session that's up to ~$34 of token spend on a file you never referenced. Power Claude flips that switch off. The chip still shows in the chat input — one click attaches the active file when you actually want it — but nothing is attached to your prompt until you opt in. Self-heals across Claude Code auto-updates.
up to ~$34/session in unspent tokens · opt-in instead of opt-out · one click to attach · self-heals across updates
Claude Code stops stealing your cursor.
Default Claude Code yanks your editor focus every time its panel reveals, output arrives, or a file is shown — break your flow once per turn, every turn. Power Claude patches the extension to pass preserveFocus:true on every autonomous reveal, show, and showTextDocument call. Your cursor stays where you put it. Patch is mtime-detected and re-applied automatically when the extension updates — no maintenance, no re-config.
addresses anthropics/claude-code#32726 · self-heals across upgrades · zero re-config · mtime-detected
ZERO CONTEXT TOKENS
UI features that work without touching your context window
The features below inject directly into VS Code and Claude Code's DOM — no prompt instructions sent to the model, no system-context additions, no output tokens burned rendering them. Power Claude patches the running webview at the UI layer so these surfaces appear for free, every session.
Every chat bubble knows what time it is.
Claude Code's chat doesn't tell you when each message happened — so when you come back to a session that was running unattended, every bubble looks like "just now." Power Claude stamps each bubble with your local HH:MM the moment it renders. Pure client-side via DOM injection — the value never enters the JSONL transcript, so it's invisible to the model and costs zero context tokens. Self-heals across Claude Code auto-updates.
HH:MM on every message · 0 context tokens · DOM-injected · self-heals across updates
SESSION EXPLORER, ENHANCED
A session list you can actually read
Power Claude enriches Claude Code's Session Explorer so a long list reads at a glance: a lifecycle glyph on every row, a live-dot on the session being driven right now, a modal that stops two windows racing the same transcript, and background tab-warming so any session opens instantly. All injected into the extension UI — no transcript writes, no token cost.
Five glyphs tell you a session's state without opening it.
Out of the box, every session in Claude Code's Session Explorer looks the same — you have to click in to find out which ones still matter. Power Claude prefixes every row with a glyph for its lifecycle state: 🟢 active, ✅ completed, 🟡 stale, ⚠️ abandoned, 📦 archived. A long list reads at a glance instead of forcing you to open each one. The classifier is deterministic — driven by transcript age, last-event type, and pending TodoWrite items — so the badge is reliable, not guessed.
5-state taxonomy · deterministic classifier · prefixed inline · O(1) glance scan
A live-dot overlay tells you which session Claude is driving this second.
Even with lifecycle badges, "active" is ambiguous — a session can be active and idle between turns. Power Claude's extension watches a heartbeat sidecar in ~/.power-claude/state/session-live/ and overlays a pulsing green dot onto the lifecycle badge whenever the heartbeat is less than 10 seconds old. You can tell at a glance which session is being driven right now versus sitting between turns waiting for input. Zero polling on the UI side — the sidecar timestamp does the work.
pulsing live dot · 10-second heartbeat · zero UI polling · disambiguates idle from running
A modal stops you racing your own JSONL writer.
Clicking Resume on a session that another VS Code window is already driving silently corrupts the JSONL transcript — both windows write concurrently and the loser's turn vanishes. Power Claude intercepts the Resume click and pops a modal: Take over (signal the other window to release the lock) or Open read-only (browse the transcript without writing). Either way, the session history stays drift-free. No more "where did my last 10 turns go?" diagnostics.
clash detection · take-over / read-only choice · prevents JSONL corruption · race-free
Open twenty sessions — and never click through them to load each one.
Power Claude is built for developers who keep many Claude Code sessions open at once. But Claude Code only loads a session's conversation when its tab is first revealed — so reopening a window with twenty sessions taxes you with twenty clicks just to wake each one. Tab Warming removes that tax. The moment VS Code finishes restoring, Power Claude reveals each open session once — using Claude Code's own open command, which reveals the existing tab, never a duplicate — to force the conversation to render, then puts you right back on the tab you were on. Loading a webview means revealing it, so the sweep is briefly visible — but it runs once, only when you've been idle a moment, speeds up adaptively when your machine keeps up, and aborts and restores your tab the instant you touch anything. On by default. Tab Warming how-to · Help hub.
reveals each open session once after restore to load it · then returns you to your tab · idle-gated + adaptive + aborts on your activity · click any tab and it is instant · on by default
Pre-summarize the conversation in the background, so the compaction freeze never has to happen.
Claude Code freezes your session for minutes when the context window fills and it has to summarize the whole conversation inline. Warm Compacting removes that wait by doing the expensive part ahead of time: while you are still approaching the limit, Power Claude pre-summarizes the earlier ~80% of the conversation in the background — stored sidecar-only, never in your live context and never touching the transcript. When the wall is near, Power Claude substitutes that pre-built compact for the early conversation and keeps the recent tail verbatim, so the context window never crosses the line that triggers the freeze — the pause simply does not happen. The recent ~20% is always kept verbatim, so the context you care about most is never lost. On by default, and no regression by design: if anything is ever off (an edited session, an unsafe cut point) it falls back to normal compaction. A brand-stamped ⚡ Warm Compact chip in the statusline and dashboard shows it working; inspect it any time with pc warm-compact. How-to guide · Self-help hub.
pre-summarizes the early ~80% in the background · sidecar-only, transcript untouched · substitutes the pre-built compact on the wire near the wall · recent tail kept verbatim · on by default · no regression — falls back to normal compaction · ⚡ statusline chip + pc warm-compact
Real numbers. Every claim is instrumented.
These charts are generated from ~/.power-claude/logs/handler.jsonl — 78.5 hours of live developer sessions, 8–12 May 2026. No synthetic data: the measured charts come straight from those logs, and the modelled ones show their inputs under the chart.
Methodology
End-to-end: detect → classify → quota exhausted → rotate. n=307 paired events from handler.jsonl.
Methodology
Modelled, not measured: each account carries its own tokens-per-minute ceiling, so N independent accounts give N× the ceiling. The bars use illustrative bases — Pro 1,000 TPM, Max 1,750 TPM — and your real per-minute limits vary by plan and change over time. The 5-hour session budgets (~44k per Pro, ~220k per Max 20×) are a separate limit; they are compared in the table below, not in this chart.
Methodology
Rate-limit overhead: hits × manual_recovery_sec. Context-switch: major switches × 23min (Leroy 2009). Approval overhead: approvals × 30s.
Methodology
Captured 8–12 May 2026 · 78.5 hours · 68 sessions. Captured with the opt-in Auto-Rotation Engine enabled (off by default). No telemetry beyond the license check unless you opt in — your key (sent over TLS, stored only as a hash), hashed machine ID, platform, extension version, and aggregate counters, plus hashed anti-abuse signals when you start the no-card trial. Nothing about your work.
What you get vs what you're paying for today
| Manual workflow | Claude Max alone ($200/mo) | Power Claude · 5 Pro + $12/mo | |
|---|---|---|---|
| Cost | |||
| Monthly cost | ~$0 (your time) | $200/mo | $83/mo Pro + $12/mo tool |
| Annual savings vs Max | — | — | ~$1,260/yr vs Max 20×, net of the $12/mo tool |
| Subscription ROI | — | — | 4.6h reclaimed covers the tool fee in week 1 |
| Recovery | |||
| Rate-limit recovery time | 45–120s manual | 45–120s manual | 4.1s median (n=307) |
| Context lost on limit hit | Yes — rebuild from scratch | Yes — rebuild from scratch | No — session persists |
| Reliability | |||
| Crash detection | Manual | Manual | 4 automated rules |
| Session recovery on crash | Restart + re-explain | Restart + re-explain | Resume from git snapshot |
| Quota | |||
| Effective 5h token budget | ~44k (one Pro) | ~220k (Max 20×) | ~220k (5× Pro independent windows) |
| 5-hour windows | 1 | 1 | 5 independent |
| Concurrent session headroom | Serialized at limit | Serialized at limit | Spread across 5 windows |
| Visibility | |||
| Haiku downgrade detection | None | None | Per-turn model attribution |
| Session history & recovery | None | None | Sessions Lane · full context |
| Token burn rate & predictor | None | None | Live analytics + runout forecaster |
| Automation | |||
| Trivial-stop recovery | Type "yes" every time | Type "yes" every time | Auto-Nudge · 11 patterns detected |
| Time | |||
| Hours reclaimed / week | 0 | 0 | ~4.6h (typical) |
| UX | |||
| VS Code sidebar | None | None | Tree view + status bar + dashboard |
Save ~$105/mo net. Fewer stalls. Start shipping.
Premium Trial: card-on-file, $0 today, 14 days — locks today's founder rate for 2 years. Free: no card, 7 days inside the extension. After billing, the 14-day refund still stands — no questions, and activating your license does not void it.
Neural-LLM is an independent software company. We are not Anthropic, PBC, and we are not affiliated with Anthropic, PBC. Claude™ is a trademark of Anthropic, PBC, used here only to identify the software Power Claude works with. Power Claude is independent third-party tooling; Neural-LLM is not affiliated with, endorsed by, or sponsored by Anthropic, PBC.