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 state-buildergit 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/state-builder)<a href="https://agentmods.dev/skills/violetfleming47/deal-intelligence/state-builder"><img src="https://agentmods.dev/badge/skills/violetfleming47/deal-intelligence/state-builder/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/violetfleming47/deal-intelligence/state-builder"><img src="https://agentmods.dev/badge/skills/violetfleming47/deal-intelligence/state-builder.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 | $0.00086 | $0.05567 |
| Opus 5.5 | $0.00034 | $0.02227 |
| Sonnet 5.5 | $0.00017 | $0.01113 |
| Haiku 4.5 | $0.00009 | $0.00557 |
Grade A, and why
state-builder 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 2mo 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 — 500 lines — stays where its author put it; the contents beside it link to each section on GitHub.
State Builder — Deal State Projection
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 references F08, the cadence-reader skill, and the supabase-reading-guide. In the starter, F08 queries return empty results and no cadence data is available. The assembler builds deal state from the 3 available reader outputs (deal-tracker, conversation-scanner, blocker-scanner). Cadence and use-case dimensions are populated when those readers are added in the full system.
You are the State Builder for {{COMPANY_NAME}}'s Deal Intelligence pipeline. You aggregate all available reader outputs from di_raw_signals and di_signal_classifications into the five-dimension di_deal_state snapshot. You are the bridge between the inbound layer and everything downstream.
Boundary
You answer one question: Given all spotter outputs since the last assembly, what is the current five-dimension state of each deal?
You do NOT:
- Read CRM or transcript provider directly. Everything comes through di_* tables (reader outputs).
- Interpret signals. You aggregate what the spotters classified. If a reader classified a contact as
primary_sponsor, you carry that forward. You don't re-assess. - Detect patterns. You produce the data that pattern detection agents consume.
- Score deals. You produce a factual snapshot.
- Recommend actions. You are pure aggregation.
- Delete or overwrite previous versions. SCD Type 2 — new version rows 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 = 'F08' 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.
- 2mo ago First seen · 500 lines · 86 tokens per session scan A eff6dd7a7652
state-builder is a skill published in the GitHub repository violetfleming47/deal-intelligence (4 stars, last pushed 5mo ago), licensed MIT. It adds 86 tokens to every session and 5,567 once invoked, about $0.0003 per session on Opus 5.5. 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
writing-workflow-skills
Use when adding a new workflow skill to pi-thinkrail-workflow, changing an existing workflow skill's role, trigger, handoff, or structure, or checking a workflow skill against the workflow system's rules. Not for authoring general-purpose skills outside this package.
writing-specs
Use when a workflow step drafts or revises a spec artifact — a goal-and-requirements, an architecture, or a module SPEC — or when a workflow skill names it at such a step. The shared quality bar for specs — not a workflow, nothing to execute.
moai-workflow-thinking
Sequential Thinking MCP for structured step-by-step analysis via --deepthink flag. Separate from UltraThink which is Claude's native extended reasoning mode. Use for multi-step analysis or architecture decisions.
mcp-host-styling-integration
Integrates MCP App UI with host theming system. Applies host CSS variables, handles onhostcontextchanged, safe area insets, display mode detection, and fullscreen configuration.
quality-hooks
Language-specific auto-lint/format/typecheck pipeline. Supports Python (ruff+pyright), TypeScript (prettier+eslint+tsc), Go (gofmt+golangci-lint). Auto-fix and convergence loops.
cog-knowledge-consolidation
Build structured knowledge frameworks from scattered vault notes with source attribution.