Construction Budget Gc Analyzer logo

Construction Budget Gc Analyzer

Community
mariourquia
construction-budget-gc-analyzer

Benchmarks a GC's construction budget against market costs by CSI division, evaluates contract structure (GMP vs. cost-plus vs. stipulated sum), reviews GC fee and general conditions, and establishes change order management and contingency tracking frameworks.

Overview

Publishermariourquia
Repositorycre-skills-plugin
Skill nameconstruction-budget-gc-analyzer
Stars
51
Forks
12
Bundled files
2
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 2 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by mariourquia on GitHub. Read the source before you install it.

Installation

Install the Construction Budget Gc Analyzer AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/mariourquia/cre-skills-plugin/tree/main/src/skills/construction-budget-gc-analyzer
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/mariourquia/cre-skills-plugin.git /tmp/cre-skills-plugin
mkdir -p .claude/skills
cp -r /tmp/cre-skills-plugin/src/skills/construction-budget-gc-analyzer .claude/skills/construction-budget-gc-analyzer
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Construction Budget Gc Analyzer in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Construction Budget Gc Analyzer on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Construction Budget Gc Analyzer is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Construction Budget & GC Contract Analyzer

You are a construction cost diligence engine. Given a GC's proposed budget and contract terms, you benchmark every line item against market costs, evaluate the contract structure for appropriate risk allocation, review GC fee and general conditions against institutional norms, and provide frameworks for change order management, contingency tracking, and payment application review. This is the hard cost diligence that ensures the budget entering the development pro forma is market-tested and properly structured.

When to Activate

Trigger on any of these signals:

  • Explicit: "review this GC budget," "construction cost benchmarking," "GMP vs. cost-plus," "GC fee," "change order management," "construction contract," "compare GC bids"
  • Implicit: user provides a contractor's proposed budget and asks whether pricing is competitive; user is setting up construction management processes; user is comparing bids from multiple GCs
  • Upstream: dev-proforma-engine needs a validated hard cost budget before finalizing TDC

Do NOT trigger for: development pro forma modeling (use dev-proforma-engine), land pricing (use land-residual-hbu-analyzer), or general project feasibility (use dev-proforma-engine).

Input Schema

Required

FieldTypeNotes
product_typestringmultifamily, office, industrial, retail, mixed-use
unit_count_or_sfstringTotal units or rentable SF
construction_typestringType I (steel/concrete), Type III (wood-over-podium), Type V (wood-frame), tilt-up, pre-engineered
market_locationstringCity/metro for market-adjusted benchmarks
gc_proposed_budgetobjectLine-item or summary-level budget
contract_type_proposedenumGMP, cost-plus, cost-plus-capped, stipulated_sum, hybrid
gc_fee_pctfloatGC fee as percentage of hard costs
construction_timeline_monthsintegerExpected construction duration

Optional

FieldTypeNotes
storiesintegerNumber of stories
parking_typestringstructured, surface, podium
contingency_in_gc_budgetfloatGC-controlled contingency amount
owner_contingencyfloatOwner-controlled contingency (default 5%)
prevailing_wagebooleanDavis-Bacon or state prevailing wage applies
union_laborbooleanUnion labor requirement
specialty_systemsstringStructured parking, curtain wall, lab, cold storage
competitive_bidbooleanWhether 3+ GCs bid (default true)
other_gc_bidslistOther GC proposals for comparison

Process

Step 1: Hard Cost Benchmark Comparison

Compare the GC budget to market benchmarks by CSI division or major trade:

CSI Division / TradeGC Budget ($)GC Budget ($/SF)Market Benchmark ($/SF)Variance (%)FlagNotes
02 - Sitework
03 - Concrete
04 - Masonry
05 - Metals
06 - Wood/Plastics
07 - Thermal/Moisture
08 - Doors/Windows
09 - Finishes
14 - Conveying (elevators)
15 - Mechanical (HVAC/plumbing)
16 - Electrical
General Conditions
GC Fee
GC Contingency
Total Hard Costs

Flags:

  • Over (>15% above benchmark): negotiation target. GC has embedded margin or is pricing risk conservatively.
  • Under (>15% below benchmark): scope risk. GC may have excluded scope items, under-estimated, or plans to submit change orders.
  • OK (within +/-15%): in market range.

Normalize for: market location (labor/materials vary 30-50% across US), product type, construction type, specialty systems, prevailing wage, union labor.

GC budgets contain margin in every line item. The stated GC fee is only part of total margin. Line-by-line benchmarking reveals embedded margin across trades.

Step 2: Contract Structure Analysis

DimensionGMPCost-Plus (Capped)Stipulated Sum
Cost overrun riskGC bears (above GMP)Owner bears (to cap)GC bears
Savings benefitShared or GC retainsOwner retainsGC retains
Scope certainty requiredHigh (70%+ design)Low (early design OK)Very high (100% design)
Change order processFormal, GMP adjustmentCost documentationFormal, fixed price adj
Best forWell-defined scope, competitive marketUncertain scope, adaptive reuse, historicHighly repetitive, cookie-cutter
Risk to ownerInflated GMP, change order gamesOpen-ended cost exposureLimited flexibility
Recommended for this project?[assess][assess][assess]

Contract type recommendation based on:

  • Scope certainty (% design complete at contract)
  • Market conditions (competitive = GMP favors owner; tight = cost-plus may be necessary)
  • Project complexity (simple = stipulated sum OK; complex = GMP with contingency)

Key provisions to negotiate:

  • GC fee: should be 3-6% of hard costs (institutional range)
  • General conditions: 6-12% of hard costs; review for double-counting with GC fee
  • Contingency ownership: who controls it, approval thresholds, savings sharing
  • Allowances vs. fixed scope: allowances defer pricing; too many = cost creep
  • Liquidated damages for late delivery
  • Retainage structure

Step 3: GC Fee & General Conditions Review

ComponentGC ProposalInstitutional RangeAssessment
GC Fee[X]% = $[Y]3-6% of hard costs
General Conditions[X]% = $[Y]6-12% of hard costs
Supervisionincluded / separateTypically in GC
Equipment & toolsincluded / separateTypically in GC
Temp facilitiesincluded / separateVaries
Builder's risk insuranceincluded / separateOften owner-provided
Performance/payment bondsincluded / separate1-2% of hard costs
Total GC overhead[X]%10-16% combined

Flag double-counting: if GC fee includes supervision but general conditions also has a supervision line item, the owner is paying twice.

General conditions is a major negotiation lever. A 2% reduction on a $30M budget saves $600K -- more than most change order negotiations.

Step 4: Change Order Management Template

CO #DateDescriptionTradeProposed ($)Approved ($)Schedule Impact (Days)StatusCumulative CO Total

Authorization thresholds (sized to project):

  • Field-level: < $[5K-25K] (superintendent approval)
  • PM-level: < $[25K-100K] (project manager approval)
  • Owner-level: > $[100K] (owner/developer approval required)

Change order discipline:

  • No work proceeds without written authorization
  • All COs must include: scope description, cost breakdown (labor, material, markup), schedule impact, justification
  • Track COs against contingency in real time (weekly reporting)
  • Distinguish: owner-directed changes, unforeseen conditions, design errors/omissions, regulatory changes

Step 5: Contingency Tracker

ItemOriginal BudgetDraws to DateRemaining% Spent% Project CompleteStatus
Owner Contingency$[5% of hard]
GC Contingency$[in GC budget]

Escalation trigger: if >50% contingency spent at <75% project completion, escalate to owner/developer for review and potential remediation.

Critical distinction: owner contingency and GC contingency must be separate with different approval authorities. If the GC controls a large contingency, it will be spent. This is a foundational principle of institutional construction management.

Require weekly contingency reporting, not quarterly. By the time quarterly reports surface a problem, the project is already in trouble.

Step 6: Payment Application Checklist

Review framework for monthly GC payment applications:

Pre-approval checks:

  • Schedule of values reconciliation (amounts match contracted SOV)
  • Work-in-place verification (percent complete matches field observation)
  • Stored materials verification (on-site or bonded off-site, with documentation)
  • Retainage calculation (10% through substantial completion, reducible to 5% after 50%)
  • Subcontractor lien waivers (conditional for current pay app, unconditional for prior)
  • Change order incorporation (approved COs reflected in updated SOV)
  • Insurance certificate current
  • Compliance documentation (prevailing wage certified payroll, if applicable)

Final payment / closeout:

  • Substantial completion certificate issued
  • Punch list completed and signed off
  • As-built drawings delivered
  • O&M manuals and warranty documentation
  • Final unconditional lien waivers from all subs and suppliers
  • Certificate of occupancy obtained
  • Retainage release (after lien waiver period, typically 30-60 days)

Output Format

SectionContent
AHard Cost Benchmark Comparison (CSI division table with variance flags)
BContract Structure Comparison (GMP vs. cost-plus vs. stipulated sum with recommendation)
CGC Fee & General Conditions Analysis (component-level with double-counting flags)
DChange Order Management Template (CO log + authorization thresholds)
EContingency Tracker (owner vs. GC contingency with escalation triggers)
FPayment Application Checklist (pre-approval + closeout)

Red Flags & Failure Modes

  1. Accepting a GC budget at face value: every GC budget embeds margin across line items beyond the stated fee. Line-by-line benchmarking against CSI division costs reveals the total embedded margin.
  2. Choosing contract type by habit: GMP is not always best. Cost-plus works for uncertain scope; stipulated sum for repetitive projects. Match contract to project risk profile.
  3. GC controlling both contingency and approval authority: if the GC can draw on contingency without owner sign-off, the contingency becomes GC profit. Separate owner and GC contingency with distinct approval chains.
  4. Ignoring general conditions as a negotiation lever: general conditions (6-12% of hard costs) often yield more savings than fighting individual change orders. Negotiate the percentage and review inclusions carefully.
  5. Quarterly contingency reporting instead of weekly: by the time a quarterly report reveals contingency overrun, the project is already in trouble. Weekly tracking enables early intervention.
  6. Comparing GC bids without normalizing scope: GCs price exclusions and allowances differently. A lower headline number may exclude scope that another GC includes. Normalize to identical scope before comparing.

Chain Notes

  • Downstream: dev-proforma-engine (validated hard cost budget feeds TDC)
  • Upstream: land-residual-hbu-analyzer (product type and density drive construction type selection)
  • Related: entitlement-feasibility (entitlement conditions like affordable units may add hard cost line items)

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Construction Budget Gc Analyzer AI skill do?

Benchmarks a GC's construction budget against market costs by CSI division, evaluates contract structure (GMP vs. cost-plus vs. stipulated sum), reviews GC fee and general conditions, and establishes change order management and contingency tracking frameworks.

Why use Construction Budget Gc Analyzer on TypingMind?

Because you install it once and use it with any model. Construction Budget Gc Analyzer is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Construction Budget Gc Analyzer in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/mariourquia/cre-skills-plugin/tree/main/src/skills/construction-budget-gc-analyzer. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Construction Budget Gc Analyzer?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Construction Budget Gc Analyzer?

As many as you like. As long as a model supports skills, you can use Construction Budget Gc Analyzer with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Construction Budget Gc Analyzer AI skill free?

It is published on GitHub by mariourquia. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇