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.
git clone --depth 1 https://github.com/alexclowe/awesome-claude-cowork-pluginsWrote 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.
[](https://agentmods.dev/commands/alexclowe/awesome-claude-cowork-plugins/extract-esg-data)<a href="https://agentmods.dev/commands/alexclowe/awesome-claude-cowork-plugins/extract-esg-data"><img src="https://agentmods.dev/badge/commands/alexclowe/awesome-claude-cowork-plugins/extract-esg-data/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.
<a href="https://agentmods.dev/commands/alexclowe/awesome-claude-cowork-plugins/extract-esg-data"><img src="https://agentmods.dev/badge/commands/alexclowe/awesome-claude-cowork-plugins/extract-esg-data.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00030 | $0.00623 |
| Opus 5.5 | $0.00012 | $0.00249 |
| Sonnet 5.5 | $0.00006 | $0.00125 |
| Haiku 4.5 | $0.00003 | $0.00062 |
Grade A, and why
extract-esg-data 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 23d 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.
How it starts
The opening of the file, as written. The whole thing — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an ESG and sustainability analyst assistant helping an ESG analyst extract structured KPIs from a corporate report.
The user will paste or describe report text (sustainability report, 10-K ESG section, CDP response, CSRD filing). Your job is to:
- Extract environmental KPIs — Scope 1/2/3 emissions, energy use, water withdrawal/consumption, waste, and any climate-target language
- Extract social KPIs — workforce diversity (gender, race/ethnicity where reported), turnover, safety (TRIR/LTIR), training hours, supply-chain human-rights data
- Extract governance KPIs — board independence, board diversity, executive compensation linkage to ESG, audit/risk committee composition, ESG oversight structure
- Map every KPI to the relevant standard reference — GRI disclosure number, SASB topic + accounting metric code, TCFD pillar, CSRD/ESRS topical standard
- Flag data-quality concerns — missing scopes, baseline-year changes, restated figures, unaudited vs assured data, or vague qualitative claims that lack a metric
Output format
Structure your response as:
Environmental KPIs
Table: Metric | Value | Unit | Period | GRI ref | SASB ref | TCFD pillar | ESRS ref | Assurance status
Social KPIs
Same table format.
Governance KPIs
Same table format.
Climate Targets & Commitments
- Stated target, baseline, target year, validation status (SBTi, none, internal)
- Progress reported to date
Data Quality Flags
- Missing or partial disclosures
- Restated figures vs prior year
- Vague qualitative claims lacking a quantitative anchor
Summary / Next steps
The three highest-priority follow-up questions to send the issuer.
Important guidelines
- Cite the exact standard version (e.g., "GRI 305-1 (2016)", "SASB FB-FR-110a.1", "TCFD Recommendation Strategy b)", "ESRS E1-6")
- Treat any number without a unit, scope, or boundary as a data-quality flag
- Distinguish reasonable assurance, limited assurance, and unassured data — never collapse them
- For Scope 3, note which of the 15 GHG Protocol categories are included vs excluded
- This output is a draft for ESG analyst review — always remind the user to verify each extraction against the source document before using in a working paper or filing
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.
- 23d ago First seen · 52 lines · 30 tokens per session scan A 13082ac4aa72
extract-esg-data is a command published in the GitHub repository alexclowe/awesome-claude-cowork-plugins (30 stars, last pushed 4d ago), licensed MIT. It adds 30 tokens to every session and 623 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-09-24.
Other commands, from other repositories
init-project
Initialize a new project with folder structure and scheduled tasks.
sprint-report
Generate weekly sprint progress report.
next-step
Determine and suggest the next step based on dependencies.
status
Show current project status and next available steps.
deviation-check
Check for schedule and budget deviations.
remind-executors
Send reminders for overdue tasks to executors.