eod-review

eod-review is a skill for Claude Code from Sundeepg98/kite-mcp-server. It costs 87 tokens per session (1,026 once invoked), scanned A, original, from a forked repository, MIT.

An end-of-day report for Indian retail traders using Zerodha Kite, an online trading platform. It reviews trading results, open positions, orders, alerts, and warnings after the market day.

In plain words
What is it for?
Use it to check daily profit and loss, holdings, open positions, orders, alerts, margin, and actions for the next trading day.
Why use it?
It gathers the day's trading details into one review, including possible issues such as intraday positions that may need closing before the market shuts.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the kite plugin — 8 skills, 3 MCP servers shipped together

Good fit Use it to check daily profit and loss, holdings, open positions, orders, alerts, margin, and actions for the next trading day.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/sundeepg98/kite-mcp-server/eod-review
Install

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.

Any agent
npx skills add Sundeepg98/kite-mcp-server --skill eod-review
Clone the repo
git clone --depth 1 https://github.com/Sundeepg98/kite-mcp-server

Made for: Claude Code.

Or install kite, the plugin that ships this one along with the rest of its 8 skills, 3 MCP servers.

Wrote 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.

agentmods badge for eod-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/sundeepg98/kite-mcp-server/eod-review/github.svg)](https://agentmods.dev/skills/sundeepg98/kite-mcp-server/eod-review)
Your own site
<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.

agentmods 80×15 button for eod-review

Your own site · 80×15
<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>
Per session 87 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,026 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin fork From a forked repository.
Token cost

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.

ModelPer sessionOnce 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

Measured 11d ago against content hash 1c1ce498d5a0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

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.

skills/eod-review/SKILL.md · 101 lines

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):

  1. trading_context — unified snapshot (margin, positions, orders, alerts, warnings).
  2. portfolio_summary — holdings P&L, top gainers/losers, invested vs current.
  3. position_analysis — detailed position breakdown (MIS vs NRML, avg price, net qty).
  4. get_orders — all orders placed today (executed, rejected, cancelled, pending).
  5. list_alerts — alert activity (triggered today, closest to trigger).
  6. Optionally get_pnl_journal for 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").

Read the full file on GitHub · 101 lines

Changes

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.

  1. 11d ago First seen · 101 lines · 87 tokens per session scan A 1c1ce498d5a0

Subscribe to this mod's changes

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.