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.
npx skills add timjensgrossinger/threnody --skill threnody-costgit clone --depth 1 https://github.com/timjensgrossinger/threnodyWrote 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/skills/timjensgrossinger/threnody/threnody-cost)<a href="https://agentmods.dev/skills/timjensgrossinger/threnody/threnody-cost"><img src="https://agentmods.dev/badge/skills/timjensgrossinger/threnody/threnody-cost/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/skills/timjensgrossinger/threnody/threnody-cost"><img src="https://agentmods.dev/badge/skills/timjensgrossinger/threnody/threnody-cost.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 | $0.00051 | $0.00724 |
| Opus 5 | $0.00026 | $0.00362 |
| Sonnet 5 | $0.00010 | $0.00145 |
| Haiku 4.5 | $0.00005 | $0.00072 |
Grade A, and why
threnody-cost 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 10d 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 — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Threnody cost dashboard
inspect_spend returns aggregated cost telemetry from local SQLite.
All data is local — no API calls. Costs are estimates based on bundled model price hints and token counts, not provider invoices.
When to use
- User asks "how much did X cost?"
- User wants to see spend trends, savings, token usage
- User wants to understand tier utilization or free-tier ratio
- User wants to see cost breakdown by role, tier, or provider
Process
-
Call
inspect_spend(MCP: Threnody) withsinceparameter.Supported windows:
24h,7d(default),30d,all. -
Format output as table:
THRENODY COST — last 7d
─────────────────────────
Subtasks: 47 Est cost: $0.34
Free: 23% Savings: $2.81 (vs all-high-tier)
BY ROLE (when present)
Implementer 28 tasks $0.18 54% of spend
Reviewer 12 tasks $0.09 26%
Architect 4 tasks $0.05 15%
Tester 3 tasks $0.02 5%
BY TIER
low 31 tasks $0.04
medium 12 tasks $0.18
high 4 tasks $0.12
BY PROVIDER
claude 38 tasks $0.27
openai 9 tasks $0.07
TIPS
- Free-tier utilization low (23%) → enable more free-tier providers
- Reviewer rework rate high → consider higher tier for review tasks
-
Each row in breakdown: role/tier/provider, task count, estimated cost, percentage of total spend.
-
If
by_roleis empty (no role-tagged tasks yet), skip BY ROLE section. -
Add contextual tips based on data:
free_subtask_pct < 30%→ "Enable more free-tier providers to cut spend"savings_usd > 0→ "Threnody saved you $X vs all-high-tier routing"- Any role with high rework rate → "Consider higher tier for {role} tasks"
Interpretation
- est_cost_usd: estimated cost based on bundled model price hints × token counts. Not a provider invoice.
- counterfactual_cost_usd: what the same work would cost if all tasks ran on high-tier model.
- savings_usd: counterfactual - est = dollars saved by tier routing.
- free_subtask_pct: percentage of subtasks that cost $0 (free-tier providers).
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.
- 10d ago First seen · 85 lines · 51 tokens per session scan A 9ffd74688105
threnody-cost is a skill published in the GitHub repository timjensgrossinger/threnody (2 stars, last pushed 14d ago), licensed Apache-2.0. It adds 51 tokens to every session and 724 once invoked, about $0.0003 per session on Opus 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 2026-08-31.
Other skills, from other repositories
stripe-refund-auditor
Audits Stripe refunds over a date range to surface anomalies (refund-rate spikes, missing reasons, duplicate refunds). Activates when the user asks to "audit refunds", "check Stripe refund anomalies", or "review refund activity".
iblai-api-billing
Operate an ibl.ai organization's billing surface via the platform API — credit accounts (balance, auto-recharge, manual top-up), transaction history, generic item paywalls (config + price tiers), Stripe Connect checkout (authenticated and guest), subscriptions, access checks, public pricing, and platform reporting…
iblai-api-spend-caps
Manage an ibl.ai organization's LLM spend caps via the platform API — admin-imposed maximum LLM cost at three scopes (tenant-wide, one agent, or one user on one agent), each with a rolling interval (day/week/month/year), a hard-block or alert-only enforcement mode, and near-limit alert thresholds. Read the current…
llm-cost-advisor
WHAT — Recommend the most cost-effective LLM provider for a given task type. Shows estimated cost per run across available providers and integrates with devcompanion llm-status to show what is actually available.
tax-filing
End-to-end corporate and personal tax preparation: data gathering from Xero/bank statements/Gmail/Obsidian/Google Drive, P&L generation, IRS compliance analysis, tax calculation, document staging, and payment guidance. Use this skill when the user mentions tax filing, tax preparation, P&L report, Form 1120, Form 1040…
personetta-set-active
Switches the active Personetta persona via set-active. The target tool is auto-detected from the host agent (Claude Code here), so no --format is needed. Use when the user asks to change recipe, switch persona, or set active role.