cc-crossbeam: Skill for Claude Code

.claude/skills/demo-contractor-corrections/SKILL.md

demo-contractor-corrections is a skill for Claude Code from mikeOnBreeze/cc-crossbeam. It costs 107 tokens per session (2,565 once invoked), scanned A, original, MIT.

A two-stage workflow for analysing a city corrections letter about an ADU permit, where an ADU is a small secondary home on a property. It reads the letter and building plans, pauses for answers, then prepares responses for the contractor.

In plain words
What is it for?
Use it to review correction-letter images or PDFs, compare them with plan sheets, research relevant building codes, and prepare a contractor response.
Why use it?
It turns scattered correction requests and plan details into specific questions and follow-up deliverables without guessing the contractor's answers.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: reads .claude/ paths; mentions subagents.

This is mikeOnBreeze/cc-crossbeam's own configuration. It tells Claude Code how to work on cc-crossbeam itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything cc-crossbeam configures →

Reuse

Borrowing it

Nothing to install: this file belongs to mikeOnBreeze/cc-crossbeam. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/mikeOnBreeze/cc-crossbeam/main/.claude/skills/demo-contractor-corrections/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/mikeOnBreeze/cc-crossbeam

Made for: Claude Code.

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 demo-contractor-corrections

README.md
[![agentmods](https://agentmods.dev/badge/skills/mikeonbreeze/cc-crossbeam/demo-contractor-corrections/github.svg)](https://agentmods.dev/skills/mikeonbreeze/cc-crossbeam/demo-contractor-corrections)
Your own site
<a href="https://agentmods.dev/skills/mikeonbreeze/cc-crossbeam/demo-contractor-corrections"><img src="https://agentmods.dev/badge/skills/mikeonbreeze/cc-crossbeam/demo-contractor-corrections/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 demo-contractor-corrections

Your own site · 80×15
<a href="https://agentmods.dev/skills/mikeonbreeze/cc-crossbeam/demo-contractor-corrections"><img src="https://agentmods.dev/badge/skills/mikeonbreeze/cc-crossbeam/demo-contractor-corrections.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 107 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,565 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.
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 $0.00107 $0.02565
Opus 5 $0.00053 $0.01282
Sonnet 5 $0.00021 $0.00513
Haiku 4.5 $0.00011 $0.00257

Measured 12d ago against content hash 89409c4938a9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

demo-contractor-corrections 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 12d 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.

.claude/skills/demo-contractor-corrections/SKILL.md · 245 lines

How it starts

The opening of the file, as written. The whole thing — 245 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Demo: Contractor Corrections Flow

Run the contractor-side corrections analysis and response locally. You are helping a contractor understand and respond to a city corrections letter on their ADU permit.

This is a two-phase flow with a pause in the middle. Phase 1 produces questions. You STOP and present them. The user answers. Then Phase 2 generates deliverables.

How to Invoke

The user provides:

  1. Corrections letter — PNG images or a PDF of the corrections letter (typically 1-3 pages)
  2. Plan binder — either a PDF path or a directory of pre-extracted PNGs
  3. (Optional) City name and project address — auto-detected from the corrections letter if not provided

Example invocations:

  • "Analyze these corrections for my Placentia ADU project. Corrections: test-assets/corrections/. Plans: test-assets/01-extract-test/pages-png/"
  • "Run the contractor flow. Corrections letter: path/to/corrections-p1.png and path/to/corrections-p2.png. Plan binder: path/to/plans.pdf"
  • "I got corrections back from the city. Here they are: [paths]"

Input Resolution

Corrections letter:

  • If PNG files: use directly with vision
  • If a directory: find all PNGs in it, sort by name, read each as a page
  • If PDF: extract to PNGs first (same as plan binder extraction below)

Plan binder:

  • If a directory of PNGs: use directly. Check for pre-existing sheet-manifest.json and title-blocks/.
  • If a PDF: extract with pdftoppm -png -r 200 "<input.pdf>" "<output-dir>/pages-png/page"

Output Directory

Create demo-output/contractor-<city>-<timestamp>/ in the workspace root. All output files go here.


PHASE 1: Analysis

Step 1.1: Parse Corrections Letter (~30 sec)

Read the corrections letter pages visually. Extract:

  • Project info: address, city, jurisdiction number, job description, date, reviewer name
  • Each correction item as a structured object:
    • Item number (preserve original numbering, including sub-items like 3a, 3b, 3c)
    • Original text (exact wording)
    • Code references (CRC, CBC, ASCE, CPC, B&P Code, municipal code)
    • Plan sheet references (Sheet A1, Detail 2/A3, etc.)
    • Review round (1st review outstanding vs. 2nd review new)
    • Bold/emphasis flags

Read the full file on GitHub · 245 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. 12d ago First seen · 245 lines · 107 tokens per session scan A 89409c4938a9

Subscribe to this mod's changes

demo-contractor-corrections is a skill published in the GitHub repository mikeOnBreeze/cc-crossbeam (291 stars, last pushed 6mo ago), licensed MIT. It adds 107 tokens to every session and 2,565 once invoked, about $0.0005 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 2026-08-30.

Related

Other skills, from other repositories

specification-writing

A workflow for writing complete patent specifications from patent claims and an invention disclosure. It adapts the document to a chosen jurisdiction, such as the US, Europe, or China.

wanshuiyin/Auto-claude-code-research-in-sleep · 49 tokens

x-scorecard

OpenSSF Scorecard for assessing open source project security. Check security best practices and compliance. Dependency: This is an x-cmd module. Install x-cmd first (see x-cmd skill for installation options). see x-cmd skill for installation.

x-cmd/x-cmd · 57 tokens

gesellschaftsrechtliche-satzungen-agb

Für Gesellschaftsrechtliche Satzungen AGB Abgrenzung: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt. Fachgebiet: AGB-Recht-Prüfer. Route: gesellschaftsrechtliche-satzungen-agb.

Klotzkette/claude-fuer-deutsches-recht · 69 tokens

nda-review

Use when the user uploads or pastes a non-disclosure agreement and asks for review, redline, risk assessment, or a recommendation on whether to sign. Identifies missing standard protections, one-sided or unusual provisions, and operational issues; produces a structured report with severity ratings and citations to…

LegalQuants/lq-ai · 79 tokens

external-purchases

US web checkout via the StoreKit External Purchase Link entitlement — currently 0% Apple commission (litigation ongoing), how to ship it safely, and how to architect for a commission flip so a future ruling is a config change, not a rewrite. Use when adding external purchase links, weighing web checkout vs IAP, or…

rshankras/claude-code-apple-skills · 76 tokens

audit-report

Generate audit reports and compliance trails using Harness audit trail data via MCP v2 tools. Track user actions, resource changes, authentication events, and access patterns across accounts, organizations, and projects. Use when asked to audit activity, generate compliance reports, investigate security incidents…

harness/harness-skills · 109 tokens