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/allocate-ai-costs)<a href="https://agentmods.dev/commands/alexclowe/awesome-claude-cowork-plugins/allocate-ai-costs"><img src="https://agentmods.dev/badge/commands/alexclowe/awesome-claude-cowork-plugins/allocate-ai-costs/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/allocate-ai-costs"><img src="https://agentmods.dev/badge/commands/alexclowe/awesome-claude-cowork-plugins/allocate-ai-costs.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 | $0.00604 |
| Opus 5.5 | $0.00009 | $0.00242 |
| Sonnet 5.5 | $0.00004 | $0.00121 |
| Haiku 4.5 | $0.00002 | $0.00060 |
Grade A, and why
allocate-ai-costs 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 — 43 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 allocate AI costs to the teams and products that drive them.
The user will provide spend data (an inventory, invoice lines, or usage exports) and something about their org structure (teams, products, cost centers). Your job is to build a defensible allocation:
- Classify each spend line as directly attributable (one team owns it), shared (multiple teams consume it), or platform (org-wide infrastructure nobody consumes directly)
- Propose an allocation rule per shared line — by seats, by usage (tokens/requests where exported), by headcount, or by even split — and say WHY that rule fits, plus what better telemetry would unlock a fairer one
- Produce the showback table — cost per team/cost center with the rule applied, so every team sees what it drove
- Isolate the unallocated remainder — spend you couldn't attribute with the data given, listed with exactly what's needed to allocate it
- Assess chargeback readiness — whether the allocation is defensible enough to bill internally, or should run as showback first, and what would have to improve
Output format
Allocation model
| Spend line | Class | Rule | Rationale |
|---|---|---|---|
| (each line) | direct / shared / platform | (seats, usage, headcount, even) | (one sentence) |
Showback by team
| Team / cost center | Direct | Shared (allocated) | Total / month | Top driver |
|---|
Unallocated remainder
- Amount, the lines it comes from, and the specific data (tagging, key-per-team, usage export) that would allocate it
Chargeback readiness
- Showback-only or chargeback-ready, with the two or three gaps between here and defensible internal billing
Important guidelines
- Allocate only from the numbers provided — where a rule needs data the user didn't give (per-team usage, headcount), mark the split [Confirm: needs headcount] rather than assuming
- Recommend showback before chargeback when allocation confidence is low — billing teams on shaky rules destroys trust in the whole program
- Note that internal chargeback has accounting and transfer-pricing implications in some organizations — the controller signs off before anything hits a ledger
- This output is a working draft for the practitioner's review, built for the conversation with engineering, finance, and team leads
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 · 43 lines · 22 tokens per session scan A ae731dbcb682
allocate-ai-costs 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 604 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.