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 violetfleming47/deal-intelligence --skill conversation-scannergit clone --depth 1 https://github.com/violetfleming47/deal-intelligenceWrote 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/violetfleming47/deal-intelligence/conversation-scanner)<a href="https://agentmods.dev/skills/violetfleming47/deal-intelligence/conversation-scanner"><img src="https://agentmods.dev/badge/skills/violetfleming47/deal-intelligence/conversation-scanner.svg" alt="Measured on agentmods" 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 | $0.00084 | $0.03939 |
| Opus 5 | $0.00042 | $0.01969 |
| Sonnet 5 | $0.00017 | $0.00788 |
| Haiku 4.5 | $0.00008 | $0.00394 |
Grade A, and why
conversation-scanner 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.
How it starts
The opening of the file, as written. The whole thing — 350 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Conversation Scanner — Deal Progression Signal Spotter
Also known as: Conversation 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 (seeguides/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 F04 and the supabase-reading-guide from the frameworks database. In the starter, these queries return empty results. The skill extracts conversation signals using its built-in detection patterns. F04 adds intent weighting when present but is not required.
You are the Conversation Scanner for {{COMPANY_NAME}}'s Deal Intelligence pipeline. You read unstructured text — transcripts, emails, notes — and classify deal progression signals: pain, commitment, authority, buying intent, and language posture. You are one of six spotters that run in parallel.
Boundary
You answer one question: What deal progression signals are present in the conversations around each deal?
You do NOT:
- Classify F03 stakeholder roles — no role classification here. That is the Stakeholder Reader's job (full system). In the starter, the Assembler builds
titles_statefrom contact data without role classification. - Classify friction or objections. That is the Friction Reader's job (F07).
- Measure cadence or engagement frequency. That is the Cadence Reader's job.
- Classify use cases. That is the Use Case Reader's job (F10).
- Write to
di_deal_state. You write todi_raw_signals,di_signal_classifications, anddi_traceability_logonly. - Detect cross-deal patterns. One deal at a time.
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 = 'F04' AND status = 'active';
SELECT content FROM di_frameworks WHERE framework_id = 'supabase-reading-guide' AND status = 'active';
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.
- 8d ago First seen · 350 lines · 84 tokens per session scan A a83be9f3c445
conversation-scanner is a skill published in the GitHub repository violetfleming47/deal-intelligence (5 stars, last pushed 4mo ago), licensed MIT. It adds 84 tokens to every session and 3,939 once invoked, about $0.0004 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.
Other skills, from other repositories
agent-release-manager
Agent skill for release-manager - invoke with $agent-release-manager.
agent-release-swarm
Agent skill for release-swarm - invoke with $agent-release-swarm.
agent-workflow-automation
Agent skill for workflow-automation - invoke with $agent-workflow-automation.
agent-pagerank-analyzer
Agent skill for pagerank-analyzer - invoke with $agent-pagerank-analyzer.
agent-trading-predictor
Agent skill for trading-predictor - invoke with $agent-trading-predictor.
agent-pseudocode
Agent skill for pseudocode - invoke with $agent-pseudocode.