borghei/Claude-Skills / business-operations/procurement-optimizer
procurement-optimizer
VerifiedCut software and services spend through seat-utilisation analysis, redundant-tool detection, and renewal-timing leverage. Use when auditing SaaS spend, preparing a renewal negotiation, or hunting a budget-reduction target.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 14.3 KB |
| assets/renewal-negotiation-brief.md | markdown | 4.2 KB |
| assets/sample_spend.json | config | 5.0 KB |
| assets/spend-audit-report-template.md | markdown | 3.5 KB |
| references/saas-negotiation-levers.md | markdown | 12.8 KB |
| references/utilization-benchmarks.md | markdown | 10.1 KB |
| scripts/license_utilization_analyzer.py | script | 8.8 KB |
| scripts/savings_opportunity_ranker.py | script | 10.9 KB |
| scripts/tool_overlap_detector.py | script | 9.5 KB |
assets/renewal-negotiation-brief.md
View on GitHub# Renewal Negotiation Brief — <vendor>
Complete before the first vendor call. A negotiation entered without a walk-away and a
target is not a negotiation.
---
## Contract facts
| Field | Value |
|-------|-------|
| Vendor / product | |
| Current annual cost | |
| Renewal date | |
| **Notice deadline** | **<date> — diary this now** |
| Auto-renew | |
| Current term | |
| Proposed uplift | |
| Vendor fiscal year-end | <find it; year-end discounts beat quarter-end ones> |
| Internal owner | |
| Criticality | critical / core / reference |
## Usage position
| Metric | Value |
|--------|-------|
| Seats purchased | |
| Seats assigned | |
| Seats active (30d) | |
| Active utilisation | |
| Category benchmark | |
| Cost per active seat | |
**Data source for active seats:** <admin export / API / SSO proxy>. If this is a proxy,
say so — the seat-reduction ask is weaker and the vendor may probe it.
## Our position
**Target seat count:** <active × 1.12, rounded>
**Target annual cost:** <amount> (<n>% below current)
**Acceptable outcome:** <amount>
**Walk-away:** <amount, or "no walk-away — critical tool, price-only negotiation">
Be honest about the walk-away. On a critical tool with no alternative there is no walk-away,
and pretending otherwise on a call is transparent to an experienced account team. In that case
the lever is volume and terms, not the threat of leaving.
## Alternative
**Named alternative:** <or "none — this is a price-only negotiation">
**Evaluation status:** <not started / trial scheduled / trial running / written comparison done>
**Switching cost estimate:** <migration effort, retraining, data export, parallel-running period>
A competitor named on a call with no evaluation behind it is worth nothing and is priced as
a bluff. Either run a real evaluation or do not mention one.
## Levers in priority order
- [ ] **Volume** — cut to <n> seats. State as a fact, not an ask. Yield: 20-40%
- [ ] **Term** — <accept / decline> multi-year. Only accept if utilisation is healthy and the discount exceeds 20%
- [ ] **Timing** — close inside vendor quarter-end <date> / year-end <date>. Yield: 5-15%
- [ ] **Alternative** — <if credible>. Yield: 10-25%
- [ ] **Payment terms** — annual up-front. Check against our cost of capital first. Yield: 2-5%
- [ ] **Reference / logo** — cap explicitly at <n> calls per year. Confirm with comms first
## Terms to secure (worth more than the headline discount)
- [ ] **Uplift cap** — target CPI-linked or 3-5% maximum
- [ ] **Seat-reduction right** at each anniversary without penalty
- [ ] **Price protection on expansion** — added seats at the same unit rate
- [ ] **Notice period** shortened to 30 days
- [ ] **Data export terms** — format, timeframe, cost, specified in contract
- [ ] Termination for convenience with pro-rata refund <if ACV > $100K>
## Anticipated vendor moves
| They say | We respond |
|----------|-----------|
| "Standard 7% uplift" | There is no standard. What changed in the product? |
| "We'll include the premium tier free" | Quote it without. Free tiers become next year's baseline |
| "Add seats and I'll improve the rate" | We are repricing the seats we need, not buying more |
| "This pricing expires Friday" | Then we will talk the following Friday |
| <escalation to our CFO> | Pre-briefed on <date> with target and walk-away |
## Timeline
| Date | Step | Owner |
|------|------|-------|
| T-150d | Pull utilisation; set target seat count | |
| T-120d | Open. State seat reduction; request pricing | |
| T-110d | Start alternative evaluation if response is weak | |
| T-90d | First counter received — do not accept it | |
| T-75d | **Serve notice** if deadline approaches | |
| T-45d | Converge; trade term or payment timing | |
| T-30d | Close inside vendor quarter-end | |
| T-0 | Record new renewal date, notice deadline, uplift cap | |
## Pre-call checklist
- [ ] Notice deadline is diarised with a reminder 14 days before
- [ ] Internal exec briefed on target and walk-away before the first call
- [ ] Owning team has confirmed the target seat count is workable
- [ ] Vendor fiscal year-end identified
- [ ] Someone other than the tool's owner is in the room — owners negotiate poorly for tools they love
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| rea-analysis-optimizationmorluto/reaOptimize REA providers and shared analysis workflows for agent context, latency, CPU, and memory while preserving correctness and Evidence. Use for analysis bottlenecks and cache or query design; CI/test-suite optimization belongs to rea-ci-tests-audit. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| rea-ci-tests-auditmorluto/reaAudit REA CI and test suites for correctness, fixture drift, false passes, and measured performance; use for suite or workflow investigations and efficiency changes, rather than ordinary feature testing or a single test failure. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| rea-tool-designmorluto/reaAudit, investigate, design, or change REA investigation tools, CLI/MCP contracts, provider capabilities, and Evidence semantics. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-auditDietrichGebert/ponytailQuality audit of the whole repo: bugs, security, real load, missing tests, speed, and what to delete. Most important first. | Stars: 194k | Updated | Claude CodeCodex | Verified | Install |