By Brisket1994
Calibrated, dual-mode tuck-in acquisition analysis for North American contracted K-12 student transportation (school bus) operators and adjacent contracted-services targets, built for an in-house corporate-development team. FULL mode (name, website, owner revenue mix, historical financials) runs a five-stage, review-gated pipeline through a screening memo; RECON mode (just a website or a name) produces a recon brief with an input-readiness diagnostic, stopping before earnings work. A mandatory Step 0 calibration confirms the run plan before any agent dispatches. See the plugin README for the full pipeline detail.
Based on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Performs a first-pass quality-of-earnings review of an acquisition target's historical financials — reconstructs the adjusted-EBITDA bridge, builds an add-back register, normalizes owner compensation, tests related-party items, assesses contract-book revenue quality and district concentration, and pegs normalized working capital. Wave 1 of the tuck-in pipeline. Read-only; produces the QoE findings memo.
Researches the target's sector and adjacent contracted-services analogs and returns a market context memo with a defensible entry/exit multiple range. Both modes — Wave 1 of the FULL pipeline, Wave R1 of the recon pipeline (sector range only in recon). Read-only; web search only — no paid data feeds.
Builds the three-statement model with a returns view in Excel and drafts the screening memo, from an approved assumption set and the QoE findings memo. Wave 3 of the tuck-in pipeline. This is the only subagent with write access.
Synthesizes the three Wave R1 outputs (target intelligence, market and multiples, web footprint scan) into a written recon brief — the deliverable of recon mode. The only subagent with write access in recon mode. Stops deliberately before any earnings work; the brief carries an explicit input-readiness diagnostic and an engagement recommendation, not a deal recommendation.
Crawls an acquisition target's website and returns a structured company profile — service lines, districts and end markets, footprint, fleet and OEM relationships, certifications, and leadership facts. Both modes — Wave 1 of the FULL pipeline, Wave R1 of the recon pipeline. Read-only; touches untrusted external web content.
Method for positioning a lower-middle-market service-business acquisition target within a valuation multiple range — identifying the company-specific quality factors that move a business up or down within the range, and stating the position without false precision. Use when converting market research and a normalized earnings base into a valuation thesis for a tuck-in.
Method for a first-pass quality-of-earnings review of a lower-middle-market service-business acquisition target — building the adjusted-EBITDA bridge, disciplining add-backs, normalizing owner compensation, scrutinizing revenue quality, pegging normalized working capital, and handling cash-basis financials. Use when reviewing a target's historical financials to establish a defensible normalized earnings base.
Structure and method for the recon brief — the deliverable of recon mode. Synthesizes the target intelligence brief, market and multiples memo, and web footprint scan into a single pre-engagement document with an input-readiness diagnostic and an engagement recommendation. Distinct from the screening memo (which is post-financials, deal-shaped); the recon brief is pre-financials and engagement-shaped. Use when drafting the recon brief for a thin-input tuck-in target.
Calibration layer that adapts an upstream private-equity memo skeleton — `private-equity:ic-memo` by default, or the lighter `private-equity:deal-screening` when the user opts in — for a Summit tuck-in first-pass screening decision. Inherits the skeleton's memo structure; supplies only the Summit / student-transportation delta — pre-LOI register, the screening recommendation vocabulary, the cash-basis caveat carry-through, the verification-debt discipline, the Summit deal-structure framing, the synergy / integration value-creation overlay, and the K-12 student-transportation risk axes. Use after the model is built, in tandem with the selected skeleton skill, when drafting the screening recommendation document for a K-12 student-transportation tuck-in target.
Sector knowledge for analyzing North American contracted K-12 student transportation (school bus) acquisition targets — operator and service-line structure, the fragmented operator landscape and the consolidators, the contract-book revenue-quality hierarchy, the certification/safety/compliance drivers of recurring revenue, the roll-up synergy stack and the precedent-deal comp set, and how to triangulate a defensible valuation multiple when no clean public comparables exist. Use when researching the market context for a student-transportation or adjacent contracted-services tuck-in.
This plugin requires configuration values that are prompted when the plugin is enabled. Sensitive values are stored in your system keychain.
firecrawl_api_keyAPI key from firecrawl.dev. Powers the hosted Firecrawl MCP server the crawl/footprint workers prefer. Enter it at enable time in EACH environment you run the plugin in (Claude Code CLI and Cowork are configured separately; keychain config does not cross apps/machines). Stored securely; never written to a plugin file. If the Firecrawl MCP is unavailable, the workers fall back to built-in WebFetch automatically — the run still completes, at reduced crawl quality.
${user_config.firecrawl_api_key}External network access
Connects to servers outside your machine
Uses power tools
Uses Bash, Write, or Edit tools
A Claude Code plugin for calibrated, dual-mode tuck-in acquisition analysis of North American contracted K-12 student transportation (school bus) operators and adjacent contracted-services businesses, built for an in-house corporate-development team. It is distributed through the summit-corp-dev marketplace defined in this repository.
A mandatory Step 0 calibration confirms the run plan before any agent dispatches.
Install the two upstream vertical plugins this pipeline depends on, then the plugin itself:
claude plugin marketplace add anthropics/financial-services
claude plugin install financial-analysis@claude-for-financial-services
claude plugin install private-equity@claude-for-financial-services
claude plugin marketplace add Brisket1994/summit-corp-dev
claude plugin install summit-corp-dev@summit-corp-dev
Then enter your Firecrawl API key when prompted (the plugin still runs without one, at reduced crawl quality) and run /summit-corp-dev:tuck-in-analysis. For the Claude Cowork install path and full setup detail, see the plugin README.
Full documentation — architecture, the build-vs-borrow rationale, dependencies, Claude Cowork install, the run contract, the pipelines, and known limitations — lives in the plugin README:
plugins/summit-corp-dev/README.md.
MIT — see LICENSE.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimnpx claudepluginhub brisket1994/summit-corp-dev --plugin summit-corp-devTransform a draft prompt, system message, CLAUDE.md, or multi-agent orchestrator into production-grade instructions for Claude Fable 5. Runs a phased optimization protocol with mandatory live calibration against Anthropic documentation; an orchestrated fan-out mode that deepens landscape research via Claude Code dynamic workflows; and no-silent-fallback deployment guidance (structured refusal categories as stop-and-surface signals; fallback events surfaced, never silently accepted). Orchestrated-research deliverables lead with an executive summary, run a load-bearing source-validation revisit pass, run an always-on verify-and-converge stage under verdict-ladder discipline, and prefer non-blocking multi-agent harness patterns over blocking orchestrators. The Phase 3 anti-pattern sweep incorporates Fable 5 / Mythos 5 system-card behavioral findings (six-pattern long-horizon failure taxonomy; elevated grader/eval awareness; over-refusal collapsed to the lowest measured to date; prompt-injection improvements with browser-legacy and prefill regressions; multi-agent turf wars; simulation-framing and survival-pressure rationalization; detect-but-execute; context anxiety; over-engineering bias). Invoke by pasting a draft with optimization intent (auto-trigger) or by typing /prompt-optimization. Ships bundled landscape-research + devils-advocate worker agents.
Upstash Context7 MCP server for up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your LLM context.
Access thousands of AI prompts and skills directly in your AI coding assistant. Search prompts, discover skills, save your own, and improve prompts with AI.
Comprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
Develop, test, build, and deploy Godot 4.x games with Claude Code. Includes GdUnit4 testing, web/desktop exports, CI/CD pipelines, and deployment to Vercel/GitHub Pages/itch.io.
Upstash Context7 MCP server for up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your LLM context.
Comprehensive feature development workflow with specialized agents for codebase exploration, architecture design, and quality review