Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add Sundeepg98/kite-mcp-server --skill eod-reviewgit clone --depth 1 https://github.com/Sundeepg98/kite-mcp-serverWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/sundeepg98/kite-mcp-server/eod-review)<a href="https://agentmods.dev/skills/sundeepg98/kite-mcp-server/eod-review"><img src="https://agentmods.dev/badge/skills/sundeepg98/kite-mcp-server/eod-review/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/sundeepg98/kite-mcp-server/eod-review"><img src="https://agentmods.dev/badge/skills/sundeepg98/kite-mcp-server/eod-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00087 | $0.01026 |
| Opus 5 | $0.00044 | $0.00513 |
| Sonnet 5 | $0.00017 | $0.00205 |
| Haiku 4.5 | $0.00009 | $0.00103 |
Grade A, and why
eod-review scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
End-of-Day Review
Run this after market close (3:30 PM IST) or as a running check anytime after lunch.
1. Gather state
Call in this order (many can be parallel):
trading_context— unified snapshot (margin, positions, orders, alerts, warnings).portfolio_summary— holdings P&L, top gainers/losers, invested vs current.position_analysis— detailed position breakdown (MIS vs NRML, avg price, net qty).get_orders— all orders placed today (executed, rejected, cancelled, pending).list_alerts— alert activity (triggered today, closest to trigger).- Optionally
get_pnl_journalfor a structured P&L entry.
2. Format the EOD report
## End-of-Day Review — <Date>
### Day Performance
- Holdings day P&L: <amt> (<pct>%)
- Positions day P&L: <amt>
- Net day P&L: <amt>
### Orders Today
- Placed: <n>
- Executed: <n>
- Rejected: <n> (reasons: <list>)
- Cancelled: <n>
- Pending AMO: <n>
### Open Positions
<If MIS positions still open AND time > 2:30 PM IST:>
WARNING: <n> MIS positions still open. Market closes 3:30 PM IST;
MIS auto-squares at 3:20 PM. Convert with `convert_position` if you
want to carry overnight.
- <symbol>: <qty>, avg <price>, P&L <amt>
<NRML / CNC positions:>
- <symbol>: <qty>, avg <price>, P&L <amt>
### Top Movers in Your Book
Gainers:
1. <symbol> +<pct>% (+<amt>)
2. ...
Losers:
1. <symbol> -<pct>% (-<amt>)
2. ...
### Alerts
- Active: <n>
- Triggered today: <list with prices>
- Closest to trigger (still armed): <symbol>, <pct>% away
### Tomorrow's Prep
- Pending AMO orders: <list> — will execute at 9:15 AM
- Convert MIS → CNC/NRML? (only if you want to carry)
- Set alerts on stocks that moved >3% today
- Review rejected orders and fix params if re-placing
3. Timing awareness
Adjust framing based on the current IST time:
- Before 3:20 PM IST: Label as "intraday check", not EOD. MIS positions can still be converted or squared manually.
- 3:20 — 3:30 PM IST: Final hour. Flag auto-square-off loud and clear if any MIS remain.
- 3:30 — 3:40 PM IST: Closing session. Positions are settling; numbers may still move.
- After 3:40 PM IST: True EOD. Numbers are final for the day.
- After market close on weekends/holidays: Show the most recent trading day's data but note it explicitly (e.g., "showing Friday's close — markets closed Sat/Sun").
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 11d ago First seen · 101 lines · 87 tokens per session scan A 1c1ce498d5a0
eod-review is a skill published in the GitHub repository Sundeepg98/kite-mcp-server (0 stars, last pushed 2mo ago), licensed MIT. It adds 87 tokens to every session and 1,026 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. It comes from a forked repository.
Other skills, from other repositories
quant-mathematician
You are a world-class applied mathematician, statistical researcher, and quantitative strategy architect.
position-optimizer
You are a top 0.1% quantitative position-sizing and risk-optimization agent.
ai-trading-agent
You are an AI trading research assistant connected to Trader Dev MCP.
strategy-optimizer
You are a top 0.1% quantitative strategy optimization agent.
mean-reversion-engineer
You are a top 0.1% quantitative trading engineer and Pine Script developer.
ai-hedge-fund
You are the manager of an AI-powered hedge fund research desk.