morning-brief

morning-brief is a skill for Claude Code from Sundeepg98/kite-mcp-server. It costs 73 tokens per session (983 once invoked), scanned A, original, from a forked repository, MIT.

A pre-market briefing for Indian retail traders using Zerodha Kite, an online trading platform. It summarizes holdings, positions, available margin, market indices, and alerts before trading begins.

In plain words
What is it for?
Use it to review NIFTY 50, BANK NIFTY, and SENSEX levels, portfolio status, alerts, watchlists, and other available market signals.
Why use it?
It puts the key start-of-day account and market information in one concise check instead of requiring several separate lookups.

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 review NIFTY 50, BANK NIFTY, and SENSEX levels, portfolio status, alerts, watchlists, and other available market signals.

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

README.md
[![agentmods](https://agentmods.dev/badge/skills/sundeepg98/kite-mcp-server/morning-brief/github.svg)](https://agentmods.dev/skills/sundeepg98/kite-mcp-server/morning-brief)
Your own site
<a href="https://agentmods.dev/skills/sundeepg98/kite-mcp-server/morning-brief"><img src="https://agentmods.dev/badge/skills/sundeepg98/kite-mcp-server/morning-brief/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 morning-brief

Your own site · 80×15
<a href="https://agentmods.dev/skills/sundeepg98/kite-mcp-server/morning-brief"><img src="https://agentmods.dev/badge/skills/sundeepg98/kite-mcp-server/morning-brief.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 73 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 983 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 $0.00073 $0.00983
Opus 5 $0.00036 $0.00491
Sonnet 5 $0.00015 $0.00197
Haiku 4.5 $0.00007 $0.00098

Measured 11d ago against content hash f30f2b6636a9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

morning-brief 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/morning-brief/SKILL.md · 88 lines

How it starts

The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Morning Brief (Indian Markets)

When the user asks for a morning brief, pre-market check, or start-of-day state:

1. Gather state (one consolidated call, then fill gaps)

Prefer the composite tool — it's one MCP round-trip instead of five:

  1. Call trading_context — returns margin, positions, orders, holdings, alerts, warnings.
  2. Call portfolio_summary — returns invested, current value, P&L, top gainers/losers.
  3. Call get_ltp with ["NSE:NIFTY 50", "NSE:NIFTY BANK", "BSE:SENSEX"] for index levels.
  4. Call list_alerts for alert status (which triggered overnight, which are active).
  5. Optionally call list_watchlists + get_watchlist to show distance-to-trigger on watched names.
  6. Optionally call get_fii_dii_flow for yesterday's institutional activity.

If trading_context is unavailable in the user's tool list, fall back to get_margins, get_positions, get_holdings individually.

2. Format the briefing

Use this shape — terse, scannable, IST timestamp at the top:

## Morning Brief — <Date> <Time> IST

### Market Indices
- NIFTY 50:   <price> (<change>%)
- BANK NIFTY: <price> (<change>%)
- SENSEX:     <price> (<change>%)

### Account Status
- Kite token: <Valid | Expired — re-auth before 9:15>
- Margin available: <amount> (<utilization>%)

### Portfolio Snapshot
- Holdings: <n> stocks, invested <amt>, current <amt>
- Overall P&L: <amt> (<pct>%)
- Day P&L: <amt>

### Positions
- Open: <n> (<MIS count> MIS, <NRML count> NRML)
- MIS auto-square at 3:20 PM IST — flag any MIS positions carried from yesterday

### Alerts
- Active: <count>
- Triggered overnight: <list with prices and times>

### Watchlist
- <name>: <count> items, closest to trigger: <symbol> at <pct>% away

### Institutional Flow (yesterday)
- FII: <net buy/sell amount>
- DII: <net buy/sell amount>

### Warnings
<List any warnings from trading_context — margin, rejected orders, expired token>

3. Indian market timing (use these as facts, not guesses)

  • Pre-open: 9:00 — 9:07 IST (order entry for price discovery)
  • Pre-open match: 9:07 — 9:15 IST
  • Regular trading: 9:15 AM — 3:30 PM IST
  • Closing session: 3:30 — 3:40 PM IST
  • AMO window: 3:45 PM — 8:57 AM next trading day
  • Kite token refresh: access tokens expire daily around 6:00 AM IST
  • Weekends and NSE holidays: no trading

Read the full file on GitHub · 88 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 · 88 lines · 73 tokens per session scan A f30f2b6636a9

Subscribe to this mod's changes

morning-brief is a skill published in the GitHub repository Sundeepg98/kite-mcp-server (0 stars, last pushed 2mo ago), licensed MIT. It adds 73 tokens to every session and 983 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.