Senpi Account Status — your standing across Senpi
A hidden engine pulls the user's standing in one real-time call; your job is to present it
cleanly: points and rank, the Senpi fee, and referral earnings.
Golden rules
- Run the engine; never hand-pull.
python3 scripts/status.py gathers points, the fee, and
referral together. Read its JSON.
- Real-time, not from memory. Points/rank move — never quote a figure from earlier in the
conversation; re-run.
- The fee comes from the data, never from memory. Quote
fee.pct as returned: 0% on a paid
plan (Pro, Advanced, Quant, and Starter for people already on it), the flat free rate without one,
free trials included.
- Tiers carry no benefit right now: no fee change, nothing unlocked. Do not bring tiers up. Never
suggest reaching, keeping or regaining a tier, and never close with a next-tier offer. If the user
asks about their tier or where it went, say tiers carry no benefit right now. Points still accrue
at the plan multiplier and still set leaderboard rank.
- Lead with what they asked. If they asked about points, lead with points + rank. Don't dump
every section if they asked one question — but the engine returns all of it so you can.
- Credits are explained, never read. No tool returns the AI-credit balance; the meter in the app
header is the balance. Rules in "AI credits — the usage meter" below.
- Plans and free credits are published; the balance is not. Quote the catalog and the end of the
milestones in "Plans & free credits" below — and only from there. A figure about this user (what
is left, what they were charged, where their bar sits) comes from their page, never from you.
How to run the engine
python3 scripts/status.py
Returns {as_of, identity, points, fee, referral, meta}:
points — total, base (Base copy-trading), perp (Hyperliquid), multiplier (the plan's
points rate), rank, rank_change.
fee — bps + pct, the Senpi fee this user pays, as the backend reports it: 0 / 0% on a
paid plan (bps is in tenths of a bp).
referral — balance_usdc (referral earnings not yet claimed).
meta.warnings / meta.degraded — narrate honestly.
- Fails open — partial data still returns valid JSON.
Output contract
Lead with the section they asked about; otherwise a tight standing card:
- Points & rank — total, base/perp split, multiplier, rank (+ change).
- Fee —
fee.pct (0% = a paid plan, no Senpi fee).
- Referral — pending
balance_usdc (and that it's claimable if > 0).
Formatting: clean, scannable, numbers from the data; emoji sparingly.
AI credits — the usage meter
Senpi agents run on AI-usage credits that come with the plan — a trial grant first, then plan
credits. The app shows what is left as the meter in the app header (users call it "the bubble" or
"my credits"), and their subscription page is the source of truth for the number. What each plan
includes is published in "Plans & free credits" below and may be quoted; how much is left depends
on your plan and your usage, and only the user's own page shows that.
- What spends them. Every message the user sends and every tool turn the agent runs. Long threads
cost more because the whole conversation is re-sent each turn — a fresh thread is cheaper than a
long one. Scheduled monitoring (a cron that re-reads a strategy) is the classic silent drain;
senpi-strategy-author/references/shadow-testing.md has the cheap alternatives.
- A running strategy is not what spends them. Its runtime ticks without a model call, so running
it does not move the meter; a
decision_mode: llm action in its runtime.yaml is the exception,
since that calls a model when it fires. A cron the agent set up to check on a strategy does move it
(each firing is a full model call), so name any the agent runs for this user. Using no credits is
not the same as needing no plan: the strategy runs on the agent, and a lapsed plan pauses both
(see "Plans & free credits").
- Not trading money. Credits cannot be traded, withdrawn, deposited into a strategy, or moved
anywhere — they are separate from the funding wallet and from every strategy budget. A shrinking
meter is usage, never a trading loss; a losing trade never touches the meter.
- You cannot read the balance. No Senpi tool returns it (
user_get_me → id / wallets / createdAt
/ referralCode; user_get_senpi_points → points / fees) and the engine has no credits
section. Point at the meter in the app header, or at their subscription page for the exact figure —
the in-app indicator surfaces only when credits run low, so a missing indicator is expected, not a
lost balance. Never invent a number, a percentage or a "roughly", and never guess what the meter
shows.
- Chat is not free of credits. Every turn spends them — including the turn that asks what a turn
cost. Say so plainly; never "nothing".
| Say |
Never say |
| "Chat and tool use spend AI credits from your plan; the meter in the app header is the balance — I can't read it from here. Longer threads cost more because the whole conversation is re-sent each turn." |
"chatting is free" / "that cost nothing" |
| "What each plan includes is published — here's the table. How much is left depends on your plan and your usage; the meter shows that." |
Any balance or percentage you did not read from the app, or a plan size you did not read from the table below |
| "Credits aren't money: they can't be traded, withdrawn or put into a strategy — your funding wallet and strategy budgets are separate." |
"credits" as a tradable or withdrawable balance |
| "The meter going down is usage — it moves with messages and tool turns, not with your trades." |
Blaming a shrinking meter on trading losses |
| "Your strategy runs on its own without the AI, so running it doesn't use credits. Chat does, and so does any scheduled check-in I run for you." |
"running the strategy costs nothing" while the agent runs a check-in cron on it; a wallet or strategy balance offered as proof about credits |
| "Your strategy doesn't use credits, but it runs on your agent, and the agent needs an active plan. If the trial ends, a renewal fails or the credits run out, the agent and your strategies pause until you subscribe or credits return." |
"no subscription is needed" / "your strategy keeps running without a plan" |
Routing. "What is the bubble / meter in the header?", "why are my credits going down?", "how much
did that cost?", "does my strategy use credits?", "can I trade / withdraw / deposit my credits?" all
come here, in any language. "Credits" (Ukrainian "кредити", Spanish "créditos") means these AI credits
unless the user says leverage, a loan or funding; when it is unclear, ask which before answering. A
credits question is answered from this section alone — no engine run, no number — and closes by
pointing at the meter. "What plans are there / how much
does it cost / what do I get on Pro / how do I get free credits / where are my milestone credits /
do I need a subscription / what happens when my trial ends" are catalog questions: answer them from "Plans & free credits" below, still without a figure
about this user.
Plans & free credits
Published facts — quote them. Billed per 30-day cycle, rolling from the user's own start date,
never a calendar month.
| Plan |
Price |
Credits |
Points per $1 volume |
| Pro (default) |
$50 |
$55 (+10%) |
1.5 |
| Advanced |
$100 |
$115 (+15%) |
2 |
| Quant |
$200 |
$240 (+20%) |
3 |
Starter ($25 a month, $25 credits, 1 point per $1 volume) is closed to new subscribers; people
already on it keep it and can upgrade, but cannot return to it after leaving.
- Every plan includes every model. Plans differ on credits and points rate only — never on model
access, so a cheaper plan never locks anyone out of the better model.
- No Senpi trading fee on any paid plan — only Hyperliquid's own exchange fees. For any other
account, quote its own
fee.pct from the engine; never state a rate from memory.
- Referrals pay 15% of a referred friend's monthly Senpi spend, for their first 12 months — from
what the friend spends on Senpi, not from their trading. A friend on $100 a month earns the referrer
$15 a month × 12 months = $180. How and when the share is paid out is not announced yet: if asked,
say so, and never describe a payout schedule, token or threshold for it.
- $1 of credit = $1 of AI usage. Full credits land at the start of the cycle and expire at the end
of it: no rollover, no top-ups, no overage. Out of credits = upgrade (instant) or wait for renewal.
- Upgrading is instant, any day — the new plan's full credits land immediately, the 30-day cycle
restarts, and unused credits are credited against the price, so they pay the difference.
Downgrading or cancelling takes effect at the next renewal, never mid-cycle; benefits are kept
until then and there are no mid-cycle refunds.
- Payment is web only (Stripe, senpi.ai/settings/subscription). The app shows plan, credits and
renewal date but links out to the web page to change anything.
- Free trial: activates when the user deploys their agent, is one-time, and expires 14 days
after activation. Never quote a trial figure — the starting amount has changed more than once;
their subscription page is the only source of truth. On expiry or exhaustion the agent stops until
they subscribe: active strategies pause, open positions are NOT auto-closed, funds untouched.
- A lapsed plan pauses everything, not just chat. Strategies run on the agent. When a trial or
plan expires, a renewal payment fails, or the cycle's credits run out, Senpi pauses the agent and
every strategy on it stops with it: no scans, no new entries, no stop moves. Open positions stay
open, and a stop-loss already resting on the exchange still triggers. Funds stay in their wallets,
withdrawable in the app. Subscribing, a successful renewal or an upgrade brings the agent and its
strategies back. You cannot see the user's plan, trial or renewal dates: point at
senpi.ai/settings/subscription, and never tell them a subscription is not needed.
Free credits — the milestones ended on 2026-10-26. Every free-credit milestone is over: your
first strategy, funding a wallet, the trading-volume ladder and the first-subscription bonus. None of
them pays any more, and the "Unlock Free AI Credits" card shows nothing. Its "Deploy your agent" row
went with it: the app built that row from the trial credit, and it was never a milestone.
- Milestone credit already earned stays until the next renewal — a different clock from the
14-day trial expiry, so credit that vanished at a renewal boundary is working as designed.
- The trial credit still activates when the user deploys their agent (see Free trial above).
- Never offer a bonus for a strategy, a deposit, volume or subscribing. If the user's own page or
card disagrees with this text, their page is right — never argue a user out of what is on their
screen.
⚠ Token scope
Every tool here is USER-scoped (the user's own account): needs a USER-scoped SENPI_AUTH_TOKEN.
App-scoped → no user resolves and meta.degraded; say so rather than reporting zeros.
Skill Attribution
Guide/analysis skill — it reads the user's standing; it does not mutate anything (claiming referral
rewards is a separate explicit action via user_claim_referral_rewards, which this skill never calls).
Install — both scripts are required
The engine is two files in scripts/: status.py (the engine) and mcp_client.py (its vendored
MCP helper, imported at runtime). Install the whole scripts/ directory — copying status.py
alone fails with No module named 'mcp_client'. Stdlib only, no other runtime dependencies.
1---2name: senpi-account-status3description: >-4 Show the user's standing across Senpi programs — points and rank, the Senpi trading fee (none on a5 paid plan), referral earnings — and explain the AI-credits usage meter. Use for "how many points6 do I have?", "what's my rank/tier?", "where did my tier go?", "what are my fees?", "my referral7 rewards", "how do referrals work?", and for credits: "what is the bubble/meter in the header?", "why are my credits going8 down?", "how much did that cost?", "does my strategy use credits?", "can I trade or withdraw my9 credits?", and for plans: "what plans are there?", "how much10 does Senpi cost?", "what do I get on Pro/Quant?", "how do I get free credits?", "where are my11 milestone credits?", "do I need a subscription to keep my strategy running?", "what happens when my12 trial ends?". Use this instead of calling user_get_senpi_points by hand. A hidden engine13 (scripts/status.py) pulls points, the fee and referral in one call; the credit14 BALANCE is explained, never read — no tool returns it — while the plan catalog and the end of the15 free-credit milestones are published here and may be quoted. Requires a USER-scoped Senpi token.16license: Apache-2.017metadata:18 source: https://skillmd.com/skills/jiayaoqijia/senpi-account-status19 author: Senpi20 version: "1.10.0"21 platform: senpi22 exchange: hyperliquid23---2425# Senpi Account Status — your standing across Senpi2627A hidden engine pulls the user's standing in one real-time call; **your job is to present it28cleanly**: points and rank, the Senpi fee, and referral earnings.2930## Golden rules3132- **Run the engine; never hand-pull.** `python3 scripts/status.py` gathers points, the fee, and33 referral together. Read its JSON.34- **Real-time, not from memory.** Points/rank move — never quote a figure from earlier in the35 conversation; re-run.36- **The fee comes from the data, never from memory.** Quote `fee.pct` as returned: `0%` on a paid37 plan (Pro, Advanced, Quant, and Starter for people already on it), the flat free rate without one,38 free trials included.39- **Tiers carry no benefit right now: no fee change, nothing unlocked. Do not bring tiers up.** Never40 suggest reaching, keeping or regaining a tier, and never close with a next-tier offer. If the user41 asks about their tier or where it went, say tiers carry no benefit right now. Points still accrue42 at the plan multiplier and still set leaderboard rank.43- **Lead with what they asked.** If they asked about points, lead with points + rank. Don't dump44 every section if they asked one question — but the engine returns all of it so you can.45- **Credits are explained, never read.** No tool returns the AI-credit balance; the meter in the app46 header is the balance. Rules in "AI credits — the usage meter" below.47- **Plans and free credits are published; the balance is not.** Quote the catalog and the end of the48 milestones in "Plans & free credits" below — and only from there. A figure about *this user* (what49 is left, what they were charged, where their bar sits) comes from their page, never from you.5051## How to run the engine5253```54python3 scripts/status.py55```5657Returns `{as_of, identity, points, fee, referral, meta}`:58- `points` — `total`, `base` (Base copy-trading), `perp` (Hyperliquid), `multiplier` (the plan's59 points rate), `rank`, `rank_change`.60- `fee` — `bps` + `pct`, the Senpi fee this user pays, as the backend reports it: `0` / `0%` on a61 paid plan (`bps` is in tenths of a bp).62- `referral` — `balance_usdc` (referral earnings not yet claimed).63- `meta.warnings` / `meta.degraded` — narrate honestly.64- Fails open — partial data still returns valid JSON.6566## Output contract6768Lead with the section they asked about; otherwise a tight standing card:69701. **Points & rank** — total, base/perp split, multiplier, rank (+ change).712. **Fee** — `fee.pct` (`0%` = a paid plan, no Senpi fee).723. **Referral** — pending `balance_usdc` (and that it's claimable if > 0).7374Formatting: clean, scannable, numbers from the data; emoji sparingly.7576## AI credits — the usage meter7778Senpi agents run on **AI-usage credits that come with the plan** — a trial grant first, then plan79credits. The app shows what is left as the **meter in the app header** (users call it "the bubble" or80"my credits"), and their subscription page is the source of truth for the number. What each plan81includes is published in "Plans & free credits" below and may be quoted; how much is **left** depends82on your plan and your usage, and only the user's own page shows that.8384- **What spends them.** Every message the user sends and every tool turn the agent runs. Long threads85 cost more because the whole conversation is re-sent each turn — a fresh thread is cheaper than a86 long one. Scheduled monitoring (a cron that re-reads a strategy) is the classic silent drain;87 `senpi-strategy-author/references/shadow-testing.md` has the cheap alternatives.88- **A running strategy is not what spends them.** Its runtime ticks without a model call, so running89 it does not move the meter; a `decision_mode: llm` action in its `runtime.yaml` is the exception,90 since that calls a model when it fires. A cron the agent set up to check on a strategy does move it91 (each firing is a full model call), so name any the agent runs for this user. Using no credits is92 not the same as needing no plan: the strategy runs on the agent, and a lapsed plan pauses both93 (see "Plans & free credits").94- **Not trading money.** Credits cannot be traded, withdrawn, deposited into a strategy, or moved95 anywhere — they are separate from the funding wallet and from every strategy budget. A shrinking96 meter is usage, never a trading loss; a losing trade never touches the meter.97- **You cannot read the balance.** No Senpi tool returns it (`user_get_me` → id / wallets / createdAt98 / referralCode; `user_get_senpi_points` → points / fees) and the engine has no `credits`99 section. Point at the meter in the app header, or at their subscription page for the exact figure —100 the in-app indicator surfaces only when credits run low, so a missing indicator is expected, not a101 lost balance. Never invent a number, a percentage or a "roughly", and never guess what the meter102 shows.103- **Chat is not free of credits.** Every turn spends them — including the turn that asks what a turn104 cost. Say so plainly; never "nothing".105106| Say | Never say |107|---|---|108| "Chat and tool use spend AI credits from your plan; the meter in the app header is the balance — I can't read it from here. Longer threads cost more because the whole conversation is re-sent each turn." | "chatting is free" / "that cost nothing" |109| "What each plan includes is published — here's the table. How much is left depends on your plan and your usage; the meter shows that." | Any balance or percentage you did not read from the app, or a plan size you did not read from the table below |110| "Credits aren't money: they can't be traded, withdrawn or put into a strategy — your funding wallet and strategy budgets are separate." | "credits" as a tradable or withdrawable balance |111| "The meter going down is usage — it moves with messages and tool turns, not with your trades." | Blaming a shrinking meter on trading losses |112| "Your strategy runs on its own without the AI, so running it doesn't use credits. Chat does, and so does any scheduled check-in I run for you." | "running the strategy costs nothing" while the agent runs a check-in cron on it; a wallet or strategy balance offered as proof about credits |113| "Your strategy doesn't use credits, but it runs on your agent, and the agent needs an active plan. If the trial ends, a renewal fails or the credits run out, the agent and your strategies pause until you subscribe or credits return." | "no subscription is needed" / "your strategy keeps running without a plan" |114115**Routing.** "What is the bubble / meter in the header?", "why are my credits going down?", "how much116did that cost?", "does my strategy use credits?", "can I trade / withdraw / deposit my credits?" all117come here, in any language. "Credits" (Ukrainian "кредити", Spanish "créditos") means these AI credits118unless the user says leverage, a loan or funding; when it is unclear, ask which before answering. A119credits question is answered from this section alone — no engine run, no number — and closes by120pointing at the meter. "What plans are there / how much121does it cost / what do I get on Pro / how do I get free credits / where are my milestone credits /122do I need a subscription / what happens when my trial ends" are **catalog** questions: answer them from "Plans & free credits" below, still without a figure123about this user.124125## Plans & free credits126127Published facts — quote them. Billed per **30-day cycle, rolling from the user's own start date**,128never a calendar month.129130| Plan | Price | Credits | Points per $1 volume |131|---|---|---|---|132| Pro (default) | $50 | $55 (+10%) | 1.5 |133| Advanced | $100 | $115 (+15%) | 2 |134| Quant | $200 | $240 (+20%) | 3 |135136Starter ($25 a month, $25 credits, 1 point per $1 volume) is closed to new subscribers; people137already on it keep it and can upgrade, but cannot return to it after leaving.138139- **Every plan includes every model.** Plans differ on credits and points rate only — never on model140 access, so a cheaper plan never locks anyone out of the better model.141- **No Senpi trading fee on any paid plan** — only Hyperliquid's own exchange fees. For any other142 account, quote its own `fee.pct` from the engine; never state a rate from memory.143- **Referrals pay 15% of a referred friend's monthly Senpi spend, for their first 12 months** — from144 what the friend spends on Senpi, not from their trading. A friend on $100 a month earns the referrer145 $15 a month × 12 months = $180. How and when the share is paid out is not announced yet: if asked,146 say so, and never describe a payout schedule, token or threshold for it.147- **$1 of credit = $1 of AI usage.** Full credits land at the start of the cycle and expire at the end148 of it: **no rollover, no top-ups, no overage**. Out of credits = upgrade (instant) or wait for renewal.149- **Upgrading is instant, any day** — the new plan's full credits land immediately, the 30-day cycle150 restarts, and unused credits are credited against the price, so they pay the difference.151 **Downgrading or cancelling takes effect at the next renewal**, never mid-cycle; benefits are kept152 until then and there are no mid-cycle refunds.153- **Payment is web only** (Stripe, senpi.ai/settings/subscription). The app shows plan, credits and154 renewal date but links out to the web page to change anything.155- **Free trial:** activates when the user **deploys their agent**, is one-time, and expires **14 days156 after activation**. **Never quote a trial figure** — the starting amount has changed more than once;157 their subscription page is the only source of truth. On expiry or exhaustion the agent stops until158 they subscribe: active strategies pause, **open positions are NOT auto-closed**, funds untouched.159- **A lapsed plan pauses everything, not just chat.** Strategies run on the agent. When a trial or160 plan expires, a renewal payment fails, or the cycle's credits run out, Senpi pauses the agent and161 every strategy on it stops with it: no scans, no new entries, no stop moves. Open positions stay162 open, and a stop-loss already resting on the exchange still triggers. Funds stay in their wallets,163 withdrawable in the app. Subscribing, a successful renewal or an upgrade brings the agent and its164 strategies back. You cannot see the user's plan, trial or renewal dates: point at165 senpi.ai/settings/subscription, and never tell them a subscription is not needed.166167**Free credits — the milestones ended on 2026-10-26.** Every free-credit milestone is over: your168first strategy, funding a wallet, the trading-volume ladder and the first-subscription bonus. None of169them pays any more, and the "Unlock Free AI Credits" card shows nothing. Its "Deploy your agent" row170went with it: the app built that row from the trial credit, and it was never a milestone.171172- **Milestone credit already earned stays until the next renewal** — a different clock from the173 14-day trial expiry, so credit that vanished at a renewal boundary is working as designed.174- **The trial credit still activates when the user deploys their agent** (see Free trial above).175- Never offer a bonus for a strategy, a deposit, volume or subscribing. If the user's own page or176 card disagrees with this text, their page is right — never argue a user out of what is on their177 screen.178179## ⚠ Token scope180181Every tool here is **USER-scoped** (the user's own account): needs a USER-scoped `SENPI_AUTH_TOKEN`.182App-scoped → no user resolves and `meta.degraded`; say so rather than reporting zeros.183184## Skill Attribution185186Guide/analysis skill — it *reads* the user's standing; it does not mutate anything (claiming referral187rewards is a separate explicit action via `user_claim_referral_rewards`, which this skill never calls).188189190## Install — both scripts are required191192The engine is **two files** in `scripts/`: `status.py` (the engine) and `mcp_client.py` (its vendored193MCP helper, imported at runtime). **Install the whole `scripts/` directory** — copying `status.py`194alone fails with `No module named 'mcp_client'`. Stdlib only, no other runtime dependencies.