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.
npx skills add gokulb20/crewm8-cfo-skills --skill cost-optimizationgit clone --depth 1 https://github.com/gokulb20/crewm8-cfo-skillsWrote 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/skills/gokulb20/crewm8-cfo-skills/cost-optimization)<a href="https://agentmods.dev/skills/gokulb20/crewm8-cfo-skills/cost-optimization"><img src="https://agentmods.dev/badge/skills/gokulb20/crewm8-cfo-skills/cost-optimization/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/skills/gokulb20/crewm8-cfo-skills/cost-optimization"><img src="https://agentmods.dev/badge/skills/gokulb20/crewm8-cfo-skills/cost-optimization.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 | $0.00033 | $0.03058 |
| Opus 5 | $0.00016 | $0.01529 |
| Sonnet 5 | $0.00007 | $0.00612 |
| Haiku 4.5 | $0.00003 | $0.00306 |
Grade A, and why
cost-optimization 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 10d 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 — 210 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cost Optimization
Run systematic cost optimization — not knee-jerk cutting, but disciplined, ongoing improvement of the company's cost structure. Renegotiate vendors, consolidate tools, automate processes, and find structural efficiencies. Goal: every dollar of spend is intentional and efficient.
Purpose
Cost optimization in startups is a constant tension: spend enough to grow, but not so much that you run out of runway. Most startups either ignore costs until a crisis (leading to panic cuts that damage the business) or slash indiscriminately (cutting growth investment along with waste). This skill provides a structured, phased approach to cost optimization — quick wins first, then structural improvements, with strategic restructuring only when necessary. The goal is to find the waste without cutting the growth.
When to Use
- "Optimize our costs"
- "Find savings in our OpEx"
- "Renegotiate vendor contracts"
- "Are we overspending anywhere?"
- "Cost reduction sprint"
- "Run a zero-based budget review"
- "Find 10% to cut without hurting growth"
Inputs Required
- Current spend data by vendor and category (from AP and subscription management)
- SaaS subscription list with users, features, and cost
- Vendor contracts and renewal dates
- Cloud infrastructure spend (AWS, GCP, Azure)
- Contractor roster with rates and hours
- Headcount data (salary, benefits, tools per person)
Quick Reference
| Phase | Timeline | Savings Potential | Risk |
|---|---|---|---|
| Quick Wins | 1-4 weeks | 5-15% of OpEx | Low |
| Structural Improvements | 1-3 months | 15-30% of targeted areas | Medium |
| Strategic Restructuring | Crisis only | 20-30%+ of total burn | Severe |
| Cost Category | % of Total Spend | Typical Savings |
|---|---|---|
| Headcount (salaries + benefits) | 65-85% | 10-30% (crisis), 0-5% (ongoing) |
| SaaS / Software | 5-15% | 15-30% |
| Cloud Infrastructure | 3-10% | 20-40% |
| Professional Services | 2-8% | 20-50% |
| Marketing / Ads | 2-10% | 20-50% with smarter spend |
| Office / Rent | 2-8% | 20-40% |
| Travel & Entertainment | 1-3% | 50-80% |
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.
- 10d ago First seen · 210 lines · 33 tokens per session scan A 42c1dd3c62e2
cost-optimization is a skill published in the GitHub repository gokulb20/crewm8-cfo-skills (2 stars, last pushed 4mo ago), licensed MIT. It adds 33 tokens to every session and 3,058 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
Invoice Automation
Automate invoice generation, sending, tracking, and payment reconciliation across accounting platforms.
correction-memory
A local memory system that stores tax-accountant corrections to transaction classifications. It matches future transactions to earlier vendor or description patterns.
nightly-batch
Batch-process all client companies overnight. Fetches unprocessed transactions from freee API, runs the full classification pipeline, and generates a summary for morning review.
tax-classifier
A system for assigning Japanese business transactions to accounting categories, called 勘定科目, and consumption-tax treatments. It checks exclusions, past corrections, keywords, and then uses AI when needed.
csv-importer
A tool for importing transaction CSV files—spreadsheet files separated by commas—from Japanese accounting software and classifying every imported row.
bank-reconciliation
Match book entries against bank or credit card statements to find discrepancies, missing transactions, and duplicates. Uses exact, near, and batch matching with balance verification. Trigger on "reconcile bank statement", "match transactions", "bank balance doesn't match", "close the books".