pf-esg-carbon-reporter

Turn a 40–100 hour/year ESG reporting workflow into a guided 2–4 hour process for $0.

An alternative to Greenly, Normative, and Sweep ($3,800–$12,000/yr). Generate draft ESG/carbon reports with GHG Protocol calculations, compliance framework mapping, and local data storage — all without SaaS licensing or vendor lock-in.

---

Why This Plugin

SMBs managing 1–10 facilities spend 40–100 hours per year on ESG/carbon reporting: manually collecting facility data, categorizing emissions, mapping compliance frameworks (GRI, CSRD, VSME, IFRS S1/S2), and formatting reports in rigid SaaS templates. Greenly, Normative, and Sweep charge $3,800–$12,000/year for this workflow but still require significant manual data entry and offer limited customization.

This plugin automates the document-heavy portions: intake normalization, GHG calculation, framework mapping, and DOCX report generation. All data stays local—no vendor cloud accounts or proprietary file formats. Perfect for finance controllers, sustainability coordinators, and operations managers who want structure without enterprise pricing.

---

Quick Start

/esg:setup
/esg:intake
/esg:calculate
/esg:map-framework
/esg:draft-report
/esg:status

Or run the full pipeline in one command:

/esg:assess

---

Commands

Command	Stage	What It Does
/esg:setup	0 — Setup	Creates workspace folders, installs python-docx, generates org config template
/esg:intake	1 — Data Entry	Parses unstructured input (CSV, email, PDF energy bills) and normalizes into structured ESG data
/esg:calculate	2 — Emissions	Maps data to GHG Protocol Scope 1/2/3, applies EPA 2025 emission factors, calculates tCO2e per category
/esg:map-framework	3 — Compliance	Maps emissions data to GRI, CSRD/ESRS, VSME, or IFRS S1/S2; flags missing disclosures
/esg:draft-report	4 — Report	Generates full ESG report DOCX with Executive Summary, Methodology, Results, Targets, and Appendices
/esg:esg-carbon-dashboard	Dashboard	Interactive visual dashboard — "show me"
/esg:status	—	Shows current project status and file inventory

---

How It Works

Each command follows a three-step pattern:

Step 1 — Gather: Claude asks conversational questions or reads your uploaded CSVs to collect facility data, energy records, and organizational information.

Step 2 — Analyze: Claude's AI interpretation layer normalizes unstructured data, identifies data quality gaps, calculates emissions with embedded EPA emission factors, maps your data to the selected compliance framework (GRI/CSRD/VSME/IFRS), and flags missing disclosures.

Step 3 — Generate: Claude fills the professional DOCX template with your data and AI analysis, producing a review-ready draft report in outbound/.

---

AI-Powered Features

• Intelligent Data Normalization: Automatically extracts and normalizes ESG data from unstructured sources (PDFs, emails, mixed-format spreadsheets), resolves ambiguous column headers, infers missing values from context, and flags data gaps for user review.
• Emissions Source Attribution: Identifies the largest emission sources, flags anomalies (e.g., unusually high Scope 2 intensity vs. sector benchmarks), and explains what each Scope category means for your specific organization's operations.
• Scope 3 Category Prioritization: Recommends which Scope 3 categories warrant deeper data collection based on your industry and operations.
• GHG Protocol Scope Classification: Automatically maps facility data to GHG Protocol Scope 1/2/3 categories with EPA 2025 emission factors, location-based and market-based Scope 2 calculations, and per-facility breakdowns.
• Compliance Framework Mapping: Maps calculated emissions to GRI disclosure requirements, CSRD/ESRS simplified 2025 criteria, VSME reporting, or IFRS S1/S2 standards; flags missing required disclosures.
• Emissions Intensity Benchmarking: Calculates tCO2e per employee, per square foot, and (if provided) per revenue unit, allowing comparison against industry benchmarks.
• Data Quality Labeling: Distinguishes primary data (utility bills, meter readings) from secondary data (industry averages, estimates), tracking data provenance throughout the workflow.

---

Comparison vs. Greenly / Normative

Feature	pf-esg-carbon-reporter	Greenly	Normative
ESG data intake	✅	✅	✅
GHG Scope 1/2/3 calculation	✅	✅	✅ (carbon only)
EPA emission factors	✅	✅	✅
GRI disclosure mapping	✅	✅	❌
CSRD/ESRS mapping	✅	✅	✅
VSME compliance	✅	❌	❌
IFRS S1/S2 mapping	✅	❌	❌
Full report DOCX generation	✅	✅	✅
AI emissions analysis	✅	❌	❌
Data quality insights	✅	Limited	Limited
Customizable templates	✅	❌	❌
Data stays local	✅	❌	❌
No vendor lock-in	✅	❌	❌
Persistent database	❌	✅	✅
Third-party audit verification	❌	✅	✅
Annual cost	Included	$3,800–$12,000	€3,000–€80,000

Best for: SMBs with 1–10 facilities managing annual or quarterly ESG reporting, teams wanting lower cost without SaaS lock-in, organizations prioritizing data privacy, and companies requiring customizable report templates.

---

Context & Performance Guide

Batching Thresholds

The plugin enforces batching limits to stay within Claude's context window:

• Facilities: Maximum 10 per /esg:intake run. For larger portfolios, run in multiple phases.
• Scope 3 suppliers: Maximum 200 entries per /esg:calculate run.
• Energy data sources: Handles CSV with up to 500 rows per facility (multiple years of utility records).

For larger ESG portfolios, split across multiple runs. The checkpoint system (.esg/project.json) tracks which facilities and frameworks have been processed.

File Layout

$WORKSPACE/
├── inbound/                    # Upload source files here (facility CSVs, energy bills, org profile)
├── processing/                 # Intermediate JSON files (intake, calculations, framework mapping)
├── outbound/                   # Final DOCX reports (ready for distribution)
├── archive/                    # Previous versions of reports
└── .esg/
    ├── config.json             # Organization config (name, jurisdiction, reporting year, framework)
    ├── org-profile.csv         # Template for org profile (filled by user)
    ├── facility-register.csv   # Template for facility listing
    ├── emissions-history.csv   # Historical data reference (user-maintained)
    ├── esg-intake.json         # Normalized intake data
    ├── esg-calculated.json     # GHG calculation results
    ├── esg-framework-map.json  # Framework mapping results
    ├── project.json            # Checkpoint/resume state tracker
    └── logs/                   # Error logs (failed-{skill}.log)

---

Estimated Cost per Use

Disclaimer: Token estimates are approximate and based on typical usage patterns measured from skill prompt sizes. Actual costs vary with input data size, conversation length, and complexity. Estimates use Claude Sonnet 4.6 pricing ($3/1M input, $15/1M output). Cowork and Claude Desktop subscription users (Pro/Max/Team) are not charged per-token — these estimates apply only to direct Anthropic API usage. Running stages individually in fresh sessions uses fewer input tokens than running the full pipeline sequentially, because pipeline mode accumulates conversation history across stages.

Per skill (run individually in a fresh session):

Stage	Skill Prompt	User Input	Total Input	Output	Est. Cost
esg-dashboard	~3.1K	~500	~6.4K	~8.0K	~$0.14
Standalone total			~6.4K	~8.0K	~$0.14

Running this skill once typically costs $0.10–$0.18 in API tokens (Claude Sonnet 4.6).

Known Limitations

1. No persistent ESG database: The plugin cannot maintain a live emissions database across sessions. You must maintain your own facility/emissions history in CSV files in the inbound/ folder. The plugin provides templates for org profile, facility register, and emissions history.

2. No third-party audit verification: All plugin outputs are unverified draft reports. If you require audit-grade ESG reports for investor disclosures or mandatory CSRD/California SB 253 filings, you must engage a qualified ESG auditor. All outputs include a mandatory ADVISORY_ONLY disclaimer for this reason.

3. No real-time emission factor updates: The plugin uses embedded EPA 2025 emission factors. If the EPA releases mid-year updates or you operate in a jurisdiction with custom factors, the plugin will use the last-embedded values. The plugin allows manual emission factor override with audit trail; update the factor CSV in .esg/ folder between sessions.

4. No multi-user collaboration: The plugin is single-user, session-based. Teams requiring simultaneous access to ESG data (finance + operations + sustainability roles) cannot co-edit in real-time. Workaround: one team member runs the plugin and exports DOCX to a shared folder (SharePoint, Google Drive) for async team review.

5. LLM context window for large Scope 3 datasets: Scope 3 calculations involving 15+ categories and 50+ suppliers may approach context limits (115K tokens). Large datasets may require chunking across multiple skill runs. The plugin handles up to 200 supplier entries per /esg:calculate run; split larger portfolios into multiple runs.

6. No regulatory filing integration: The plugin cannot submit reports to regulatory bodies (CSRD registry, SEC EDGAR, California Air Resources Board). You must export the DOCX/PDF manually and upload to the appropriate regulatory portal.

7. GWP version management: The plugin defaults to IPCC AR6 GWP values for 2026+ reporting. If your regulatory requirement specifies AR5, you must manually update the config and re-run /esg:calculate. Both versions are documented in calculation output metadata.

---

Requirements

• Python 3.8+ with python-docx >= 0.8.11 (auto-installed by /esg:setup)
• Claude with Read, Write, Bash, Glob tools enabled
• Workspace folder selected in Cowork (or equivalent file access)
• CSV knowledge base files maintained by user in inbound/ folder (facility register, energy records, org profile)

---

DISCLAIMER: All ESG reports generated by this plugin are drafts for internal review only. This plugin is not a substitute for professional ESG consulting or audit review. Consult a qualified ESG professional before external disclosure or regulatory filing. Incorrect emissions calculations or framework mapping could lead to regulatory non-compliance or misrepresentation claims.

Important Disclaimers

• AI-Generated Content: This plugin uses AI (LLM) technology which can produce inaccurate or incomplete outputs. All content should be treated as a starting point and reviewed for accuracy before use.
• Not Professional Advice: Outputs do not constitute legal, financial, tax, medical, or other professional advice. Consult qualified professionals before making decisions based on generated content.
• No Compliance Guarantee: References to industry standards, regulations, or guidelines are for informational purposes only. This plugin does not guarantee compliance with any law or regulation. Users are responsible for verifying all outputs meet their specific regulatory requirements.
• No Endorsement or Affiliation: Mention of third-party products, standards, or organizations does not imply endorsement, partnership, or certification by those entities.
• Not Financial or Tax Advice: Financial calculations, tax estimates, and related outputs are for informational purposes only. Consult a qualified CPA or financial advisor for tax and financial decisions.