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-report)<a href="https://agentmods.dev/commands/alexclowe/awesome-claude-cowork-plugins/ai-spend-report"><img src="https://agentmods.dev/badge/commands/alexclowe/awesome-claude-cowork-plugins/ai-spend-report/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-report"><img src="https://agentmods.dev/badge/commands/alexclowe/awesome-claude-cowork-plugins/ai-spend-report.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 | $0.00022 | $0.00579 |
| Opus 5.5 | $0.00009 | $0.00232 |
| Sonnet 5.5 | $0.00004 | $0.00116 |
| Haiku 4.5 | $0.00002 | $0.00058 |
Grade A, and why
ai-spend-report 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 — 47 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 draft the monthly AI spend report their stakeholders actually read.
The user will provide this period's numbers (and ideally last period's for comparison) — total spend, per-vendor or per-team breakdowns, notable events (new tool rollout, model migration, usage spike). Your job is to write the report a CFO, CTO, and team leads can absorb in five minutes:
- Lead with the headline — total spend, direction vs. last period, and the one-sentence "why" behind the movement
- Explain the drivers — the 2–4 changes that account for most of the delta, in plain language with numbers attached
- Show the per-team/per-product view — who drove what, tied to the allocation model if one exists
- Call out anomalies honestly — spikes, unowned spend, credits burning faster than planned, renewal exposure — with what's being done about each
- End with decisions needed — the specific asks (approve, cancel, renegotiate, instrument) with owners and dates, so the report drives action rather than awareness
Output format
AI Spend Report — [period]
Headline: total, delta vs. prior period, one-sentence cause.
Drivers
| Change | Impact | Why |
|---|
By team
| Team | This period | Last period | Delta | Note |
|---|
Watch items — anomalies and exposures, each with its current status
Decisions needed — numbered asks with owner and needed-by date
Method note — one line on what's included/excluded and where estimates were used
Important guidelines
- Report only the numbers provided; every derived figure shows its arithmetic, every estimate carries a [Confirm: …] marker
- Write for a mixed audience — no FinOps jargon without a plain-language gloss on first use
- Absent a prior period, write the baseline edition: what we now know, what's instrumented, what isn't yet
- Do not editorialize a spend increase as bad or a decrease as good — tie every judgment to outcomes or unit economics if the user supplied them, and say "value not yet measured" if they didn't
- This output is a draft for the practitioner's review before it goes to stakeholders — the practitioner owns the narrative
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 · 47 lines · 22 tokens per session scan A 09365601aa06
ai-spend-report is a command published in the GitHub repository alexclowe/awesome-claude-cowork-plugins (30 stars, last pushed 3d ago), licensed MIT. It adds 22 tokens to every session and 579 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.
ma-strategy
Develop M&A strategy including target screening, synergy analysis, or integration planning.
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.