vertical-construction

vertical-construction is a skill for Claude Code from avelikiy/great_cto. It costs 150 tokens per session (2,600 once invoked), scanned A, original, MIT.

A construction-industry reference for designing software used by contractors, architects, project managers, and field crews. It explains terms and financial processes such as bids, takeoffs, retainage, change orders, lien waivers, and draw schedules.

In plain words
What is it for?
Use it when specifying bidding, estimating, project management, subcontractor, billing, field-reporting, or construction-document products.
Why use it?
It helps prevent construction software from treating contractor billing and project work like ordinary office or SaaS workflows.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Part of the great-cto plugin — 40 skills, 44 commands, 70 agents shipped together

Good fit Use it when specifying bidding, estimating, project management, subcontractor, billing, field-reporting, or construction-document products.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/avelikiy/great_cto/vertical-construction
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 avelikiy/great_cto --skill vertical-construction
Clone the repo
git clone --depth 1 https://github.com/avelikiy/great_cto

Made for: Claude Code.

Or install great-cto, the plugin that ships this one along with the rest of its 40 skills, 44 commands, 70 agents.

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 vertical-construction

README.md
[![agentmods](https://agentmods.dev/badge/skills/avelikiy/great_cto/vertical-construction/github.svg)](https://agentmods.dev/skills/avelikiy/great_cto/vertical-construction)
Your own site
<a href="https://agentmods.dev/skills/avelikiy/great_cto/vertical-construction"><img src="https://agentmods.dev/badge/skills/avelikiy/great_cto/vertical-construction/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.

agentmods 80×15 button for vertical-construction

Your own site · 80×15
<a href="https://agentmods.dev/skills/avelikiy/great_cto/vertical-construction"><img src="https://agentmods.dev/badge/skills/avelikiy/great_cto/vertical-construction.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 150 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,600 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00150 $0.02600
Opus 5 $0.00075 $0.01300
Sonnet 5 $0.00030 $0.00520
Haiku 4.5 $0.00015 $0.00260

Measured 7d ago against content hash 3b8e52b781b1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

vertical-construction 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 7d 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/vertical-construction/SKILL.md · 171 lines

How it starts

The opening of the file, as written. The whole thing — 171 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Vertical: construction — don't spec it naive

Construction has its own money physics. A spec that treats a contractor's billing like a SaaS invoice will ship something no contractor can use, because the cash flow it ignores (retainage held back, draws against a schedule of values, subs gated on lien waivers) is the thing the contractor is trying to manage. This skill gives architect and pm the vocabulary and the non-obvious rules so the four construction products are specced from domain reality, not intuition.

The four products and their incumbents:

Product Archetype Wedge against
bid-builder marketplace-lite Excel (small contractors estimate in spreadsheets)
project-mgmt crud Buildertrend, Contractor Foreman
subcontractor-portal marketplace-lite Procore, manual COI/payment tracking
field-docs crud Procore field tools, paper daily reports

Incumbents: Procore (enterprise, ~$375+/mo minimum — too expensive and heavy for small contractors; do not fight it head-on), Buildertrend (residential-focused), Contractor Foreman, Autodesk Construction Cloud (enterprise). The opening is small contractors priced and complexity'd out of these.

Domain vocabulary (use these terms exactly in specs)

  • Estimate — internal cost calculation (what the job will cost the contractor). Bid — the priced number submitted to win the job (estimate + markup). Proposal — the customer-facing document wrapping the bid with scope, terms, exclusions. Estimate → bid → proposal are three artifacts, not synonyms.
  • Takeoff (quantity takeoff) — counting/measuring quantities from plans (sq ft of drywall, linear ft of pipe) that feed the estimate. Garbage takeoff = garbage bid.
  • Unit cost + assembly — an estimate is built from line items priced per unit (e.g. $/sq ft). An assembly bundles several unit-cost items into one (a "door assembly" = door + frame + hardware + labor). Real estimating is assemblies, not freehand numbers.
  • Markup vs margin — markup is added on top of cost (cost × 1.20). Margin is the cut of the bid price (price − cost) / price. 20% markup ≠ 20% margin. Mixing them mis-prices the job. Spec which one a field means.
  • Change order (CO) — a contracted change to scope/price after the bid is signed. Untracked COs are where margin leaks and disputes start.
  • RFI (request for information) — formal question to the architect/owner about ambiguous plans; the answer can change scope (→ change order).
  • Submittal — contractor's proposed material/product samples sent for approval before install.
  • Draw schedule + progress billing — payment isn't lump-sum. The contractor bills in draws as work completes, against a schedule of values (the job broken into line items each with a contract value); each billing claims a % complete per line.
  • Retainage / retention — the owner withholds a slice (typically 5–10%) of each payment until the job is complete/accepted. It is owed money the contractor can't touch yet — a first-class concept, not a discount.
  • Lien / lien waiver — a mechanic's lien is a legal claim against the property for unpaid work; a lien waiver is the sub/supplier signing away that right in exchange for payment. Conditional (on payment clearing) vs unconditional (already paid).
  • AIA G702/G703 — the industry-standard pay-application forms. G702 is the summary (application + certificate for payment); G703 is the continuation sheet (the schedule of values with this-period / to-date / retainage columns). Many owners require these exact forms.
  • 1099 subcontractor — subs are typically 1099 contractors, not employees; the GC must collect a W-9 and issue a 1099 for tax reporting.
  • COI (certificate of insurance) — proof a sub carries required insurance; must be current (not expired) before the sub works or gets paid.
  • Daily log — the dated field record (crew on site, work done, weather, deliveries, delays). It is legal/dispute evidence, not a status update.
  • Punch list — the end-of-job list of defects/incomplete items to fix before final payment / retainage release.
  • Schedule of values (SOV) — the contract sum allocated across work items; the backbone of progress billing and G703.

Read the full file on GitHub · 171 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. 7d ago First seen · 171 lines · 150 tokens per session scan A 3b8e52b781b1

Subscribe to this mod's changes

vertical-construction is a skill published in the GitHub repository avelikiy/great_cto (92 stars, last pushed yesterday), licensed MIT. It adds 150 tokens to every session and 2,600 once invoked, about $0.0007 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 2026-09-03.

Related

Other skills, from other repositories

pm

Project manager for GitHub issues: brainstorm design approaches, create structured issues optimized for LLM agent teams, triage and recommend what to work on next, audit and clean up stale issues, or deep-validate a single issue against the codebase. Triggers: create issue, plan work, new task, project manager, write…

rube-de/cc-skills · 98 tokens

tpp-orchestrate

Work through a queue of Technical Project Plans serially — delegate each to a TDD subagent, get a cross-model second opinion, empirically vet every finding, and make one coherent commit per plan. Use when executing a documented plan queue such as todo/ or feat-name/ for a port, migration, or multi-stage feature.

photostructure/coding-skills · 75 tokens

tpp

Work on a Technical Project Plan — read the plan, identify the current phase, do that phase's work, and update the plan with discoveries. Use when starting or resuming multi-session work tracked in a plan file.

photostructure/coding-skills · 47 tokens

handoff

Update the active Technical Project Plan for handoff when context is running low or the session is ending, so the next session continues instead of restarting.

photostructure/coding-skills · 32 tokens

terry

Invoke when orchestrating a FLEET of parallel long-running agent tasks via a priority-queue manager over git worktrees, OR when you want a producer-consumer task queue for agents that caps concurrency to avoid OOM and pace token spend on a budget — agent queue + task list + dispatched agents + a self-pacing heartbeat…

drubinstein/terry · 106 tokens

spec-drift

Standalone plan-vs-code audit on any branch: runs /ship Step 8's plan-completion section from disk (hash-pinned) against an explicit plan and base. Report, JSON, exit code. Never edits code.

Paretofilm/superpowers-gstack · 51 tokens