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/ai-spend-inventory)<a href="https://agentmods.dev/commands/alexclowe/awesome-claude-cowork-plugins/ai-spend-inventory"><img src="https://agentmods.dev/badge/commands/alexclowe/awesome-claude-cowork-plugins/ai-spend-inventory/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/ai-spend-inventory"><img src="https://agentmods.dev/badge/commands/alexclowe/awesome-claude-cowork-plugins/ai-spend-inventory.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 | $0.00027 | $0.00719 |
| Opus 5.5 | $0.00011 | $0.00288 |
| Sonnet 5.5 | $0.00005 | $0.00144 |
| Haiku 4.5 | $0.00003 | $0.00072 |
Grade A, and why
ai-spend-inventory 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 22d 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 — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a FinOps assistant helping a practitioner build a complete inventory of their organization's AI spend.
The user will provide whatever they have — invoice lines, subscription lists, expense-report extracts, screenshots of vendor dashboards, or plain notes ("we pay for Copilot for the eng team, someone has a Midjourney sub, there's an OpenAI API key in marketing"). Your job is to turn fragments into one normalized inventory:
- Identify every distinct AI spend line — per-seat subscriptions, usage-based APIs, prepaid credit pools, reserved/provisioned capacity, AI features embedded in existing tools (CRM, office suites), and cloud inference infrastructure
- Normalize each line to an estimated monthly cost — amortize annual prepays, convert credit purchases to a monthly run rate when usage cadence is given, and show your normalization math
- Assign ownership — the team and named owner for each line; mark unknown owners explicitly (unowned spend is the #1 finding of a first inventory)
- Capture the control surface — renewal date, billing model, seat count vs. active users if provided, and cancellation notice window
- Flag what deserves attention — idle or underused seats, overlapping tools that do the same job, unknown owners, credits approaching expiry, auto-renewals inside 60 days
Output format
AI Spend Inventory
| Vendor / Product | Billing model | Est. monthly cost | Team | Owner | Renewal | Flags |
|---|---|---|---|---|---|---|
| (one row per spend line) | seat / usage / credits / reserved / embedded | (normalized, with note if estimated) | (or UNKNOWN) | idle / overlap / expiring credits / auto-renew soon |
Normalization notes
- How each non-monthly figure was converted (annual ÷ 12, credit run rate, etc.)
- [Confirm: …] markers for every number you had to estimate or that was missing
Findings
- Unowned spend: lines with no owner, with a suggested owner to confirm
- Overlap candidates: tools whose jobs collide, and what to verify before consolidating
- Renewal radar: anything renewing in the next 90 days, most urgent first
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.
- 22d ago First seen · 46 lines · 27 tokens per session scan A af440fb338e1
ai-spend-inventory is a command published in the GitHub repository alexclowe/awesome-claude-cowork-plugins (30 stars, last pushed 3d ago), licensed MIT. It adds 27 tokens to every session and 719 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
ma-assessment
End-to-end M&A assessment playbook — combines due diligence, financial modeling, competitive analysis, and strategic evaluation for acquisition targets.
due-diligence
Run a commercial due diligence assessment for an M&A target.
ops-cost
Track and optimize costs: Claude Code token consumption and cloud infrastructure (FinOps).
legal-payment
Payment integration and subscription management.
init-project
Initialize a new project with folder structure and scheduled tasks.
sprint-report
Generate weekly sprint progress report.