deal-tracker

deal-tracker is a skill for Claude Code, Codex from violetfleming47/deal-intelligence. It costs 94 tokens per session (4,006 once invoked), scanned A, original, MIT.

A skill that reads structured CRM deal fields such as stage, value, owner, and close date. CRM means customer-relationship-management software used to track sales opportunities.

In plain words
What is it for?
Use it to detect deal-stage transitions, value changes, owner reassignments, and changes to expected close dates for a sales pipeline.
Why use it?
It identifies objective changes in sales records without needing to interpret emails, call transcripts, or other free-form text.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to detect deal-stage transitions, value changes, owner reassignments, and changes to expected close dates for a sales pipeline.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/violetfleming47/deal-intelligence/deal-tracker
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 violetfleming47/deal-intelligence --skill deal-tracker
Clone the repo
git clone --depth 1 https://github.com/violetfleming47/deal-intelligence

Made for: Claude Code, Codex.

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 deal-tracker

README.md
[![agentmods](https://agentmods.dev/badge/skills/violetfleming47/deal-intelligence/deal-tracker.svg)](https://agentmods.dev/skills/violetfleming47/deal-intelligence/deal-tracker)
Your own site
<a href="https://agentmods.dev/skills/violetfleming47/deal-intelligence/deal-tracker"><img src="https://agentmods.dev/badge/skills/violetfleming47/deal-intelligence/deal-tracker.svg" alt="Measured on agentmods" height="20"></a>
Per session 94 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,006 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 original No closer match found in the catalogue.
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 $0.00094 $0.04006
Opus 5 $0.00047 $0.02003
Sonnet 5 $0.00019 $0.00801
Haiku 4.5 $0.00009 $0.00401

Measured 8d ago against content hash 089e6e4d2481, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

deal-tracker 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 8d 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/deal-tracker/SKILL.md · 436 lines

How it starts

The opening of the file, as written. The whole thing — 436 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Deal Tracker — Structured Property Spotter

Also known as: Deal Properties Reader (in pipeline diagrams)

Adapting this skill: All CRM-specific values are wrapped in {{PLACEHOLDER}} markers. Before deploying, pull your CRM and transcript provider schemas (see guides/data-mapping-guide.md), map your field names and stage IDs to the placeholders, and hardcode them into this skill. The logic and structure are universal — only the field names and API calls change.

Starter note: This skill loads F08 and the supabase-reading-guide from the frameworks database. In the starter, these queries return empty results. The skill classifies signals using F02 signal definitions and its own built-in logic. F08 benchmarks enhance classification confidence when present but are not required.

You are the Deal Tracker for {{COMPANY_NAME}}'s Deal Intelligence pipeline. You read structured CRM deal properties — stage, value, owner, close date — and detect changes. You are the lightest spotter. The other five interpret unstructured text; you read structured fields where the meaning is objective.

Boundary

You answer one question: What deal property changes have occurred — stage transitions, value changes, owner reassignments, close date shifts?

You do NOT:

  • Interpret conversation content. Other spotters do that.
  • Classify stakeholder roles (per F03). The Stakeholder Reader does that (full system). In the starter, the Assembler builds titles_state from contact data without role classification.
  • Assess why a stage changed. You record that it changed, the direction, and the magnitude.
  • Write to di_deal_state. You write to di_raw_signals, di_signal_classifications, and di_traceability_log only.

Framework Loading

Load each framework individually (single query per framework to avoid MCP response size limits):

SELECT content FROM di_frameworks WHERE framework_id = 'F02' AND status = 'active';
SELECT content FROM di_frameworks WHERE framework_id = 'F08' AND status = 'active';
SELECT content FROM di_frameworks WHERE framework_id = 'supabase-reading-guide' AND status = 'active';

Read the full file on GitHub · 436 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. 8d ago First seen · 436 lines · 94 tokens per session scan A 089e6e4d2481

Subscribe to this mod's changes

deal-tracker is a skill published in the GitHub repository violetfleming47/deal-intelligence (5 stars, last pushed 4mo ago), licensed MIT. It adds 94 tokens to every session and 4,006 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.