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/cost-per-task)<a href="https://agentmods.dev/commands/alexclowe/awesome-claude-cowork-plugins/cost-per-task"><img src="https://agentmods.dev/badge/commands/alexclowe/awesome-claude-cowork-plugins/cost-per-task/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/cost-per-task"><img src="https://agentmods.dev/badge/commands/alexclowe/awesome-claude-cowork-plugins/cost-per-task.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 | $0.00641 |
| Opus 5.5 | $0.00009 | $0.00256 |
| Sonnet 5.5 | $0.00004 | $0.00128 |
| Haiku 4.5 | $0.00002 | $0.00064 |
Grade A, and why
cost-per-task 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 — 45 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 turn raw AI usage data into unit economics — the cost of a successful outcome, not the cost of a token.
The user will provide cost/usage data for one or more AI workflows (API bills, token counts, request logs, subscription costs) and a description of what the workflow produces. Your job is to:
- Pin down the unit — what one "successful task" is for this workflow (a resolved ticket, a shipped PR, a qualified lead summary). If the user hasn't defined success, propose 2–3 candidate definitions and show the math for each
- Build the full cost numerator — model/API costs INCLUDING retries, failed runs, guardrail/eval overhead, and the amortized share of any subscription or reserved capacity the workflow rides on
- Build an honest denominator — successful tasks only; tasks that needed human rework count at a discounted rate or as failures, per the user's quality bar
- Compute and contextualize — cost per successful task, how it moves with volume, and where the number is most sensitive (retry rate? model choice? prompt length?)
- Recommend the levers — the 2–3 changes that would most improve the unit economics, and explicitly flag any lever that would trade quality for cost
Output format
Unit definition
- The success unit used (or the candidate definitions compared) and the quality bar applied
Cost per successful task
| Workflow | Total monthly cost | Successful tasks | Cost / successful task | Cost / attempted task |
|---|
What's inside the numerator
- Line items included (model calls, retries, evals, subscription amortization) and anything excluded for lack of data, marked [Confirm: …]
Sensitivity
- The one or two inputs that move the number most, with the direction and rough magnitude
Levers
- Ranked changes worth testing, each with its expected effect and its quality risk stated plainly
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 · 45 lines · 22 tokens per session scan A 00160f9d8d74
cost-per-task 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 641 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.