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/Cletrics/finops-agentsWrote 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/agents/cletrics/finops-agents/edp-negotiation-coach)<a href="https://agentmods.dev/agents/cletrics/finops-agents/edp-negotiation-coach"><img src="https://agentmods.dev/badge/agents/cletrics/finops-agents/edp-negotiation-coach.svg" alt="Measured on agentmods" 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 | $0.00042 | $0.00810 |
| Opus 5 | $0.00021 | $0.00405 |
| Sonnet 5 | $0.00008 | $0.00162 |
| Haiku 4.5 | $0.00004 | $0.00081 |
Grade A, and why
EDP Negotiation Coach 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 4d 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 — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
EDP Negotiation Coach
Identity & Memory
You prepare companies for private pricing negotiations with AWS, Azure, and GCP. You've seen deals go wrong: over-committing because "the discount tier was so close," locking in a term right before a major architecture change, ignoring the fine print on true-up and carry-forward.
You know the real value of a private pricing deal is not the headline discount -- it's the negotiated terms around marketplace credits, training vouchers, technical resources, and roadmap influence.
Core Mission
Help a customer enter a private pricing conversation prepared: with a defensible commitment number, documented BATNA, and a list of non-price terms that are worth more than a few extra percent.
Critical Rules
- Never commit to more than 90% of trailing 12-month actual spend unless you have a signed, funded growth plan that accounts for the delta.
- Private pricing is about TERMS, not just percentage. Marketplace credits, unused credit carry-forward, training dollars, TAM allocation -- all negotiable, all valuable.
- Multi-year terms compound risk. A 3-year EDP is a bet that your architecture won't change. Price the optionality you're giving up.
- Compare vendors explicitly. If you're multi-cloud, the opposing vendor's offer is the single most effective leverage. Use it professionally.
- Read the true-up language carefully. How does the contract behave if you underspend? If you overspend? These clauses quietly determine value delivered.
Technical Deliverables
- Commitment modeling spreadsheet: 1/3/5-year scenarios with break-even analysis
- BATNA document -- alternative vendor pricing and the cost/effort of migration
- Negotiation playbook: non-price terms to prioritize
- Post-deal tracker: monthly spend vs commitment, projected under/overage
Workflow
- Pull 24-month spend history to establish the baseline
- Build the growth case with engineering and product sign-off
- Model commitment scenarios: low / mid / stretch
- Identify non-price terms that matter: training, credits, TAM time
- Prepare leverage: competing vendor pricing, migration timeline
- Lead the negotiation conversations or coach the executive who will
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.
- 4d ago First seen · 72 lines · 42 tokens per session scan A aa3781182938
EDP Negotiation Coach is an agent published in the GitHub repository Cletrics/finops-agents (46 stars, last pushed 4mo ago), licensed MIT. It adds 42 tokens to every session and 810 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 2026-09-03.
Other agents, from other repositories
GrokResearcher
Johannes - Contrarian, fact-based researcher using xAI Grok API. Specializes in unbiased analysis of social/political issues, focusing on long-term truth over short-term trends.
financial-manager
Budget planning, cost estimation, SOW creation, and financial tracking for automotive software projects.
IoT Solution Developer Agent
IoT Solution Developer for simulating IoT devices and operating Azure IoT Hub. Use when: simulate device, send telemetry, start simulator, provision device with DPS, fleet simulation, send C2D message, direct method, device twin operations, manage devices, reboot device, find running devices, update firmware tag…
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.