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 hoangsonww/Claude-Code-Agent-Monitor --skill model-savingsgit clone --depth 1 https://github.com/hoangsonww/Claude-Code-Agent-MonitorWrote 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/hoangsonww/claude-code-agent-monitor/model-savings)<a href="https://agentmods.dev/skills/hoangsonww/claude-code-agent-monitor/model-savings"><img src="https://agentmods.dev/badge/skills/hoangsonww/claude-code-agent-monitor/model-savings/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/hoangsonww/claude-code-agent-monitor/model-savings"><img src="https://agentmods.dev/badge/skills/hoangsonww/claude-code-agent-monitor/model-savings.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00088 | $0.00995 |
| Opus 5 | $0.00044 | $0.00498 |
| Sonnet 5 | $0.00018 | $0.00199 |
| Haiku 4.5 | $0.00009 | $0.00100 |
Grade A, and why
model-savings 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 13d 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 — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Model Savings
Quantify how much spend you would recover by moving eligible work to a cheaper model.
Input
The user provides: $ARGUMENTS
This is the routing question — e.g. "Opus → Sonnet", "move simple work to Haiku",
or empty (analyze every premium model against the next tier down). If no target family
is named, default to proposing the next-cheaper tier per model and say so.
Data Sources
| Endpoint | Returns |
|---|---|
GET /api/pricing |
{ pricing: [{ model_pattern, display_name, input_per_mtok, output_per_mtok, cache_read_per_mtok, cache_write_per_mtok }] } — the rate card for every family |
GET /api/pricing/cost |
{ total_cost, breakdown: [{ model, input_tokens, output_tokens, cache_read_tokens, cache_write_tokens, cost, matched_rule }] } — current spend and the exact token mix per model |
GET /api/sessions?limit=200 |
Sessions with model, inline cost, and metadata (turn_count, thinking_blocks) — used to judge which work is eligible to downshift |
GET /api/analytics |
agent_types, tool_usage, total_subagents — corroborate which task types are low-complexity and safe to route cheaper |
Savings method
For each candidate model in the cost breakdown, re-price its exact token mix at the target family's rates:
cost_at_target = (input_tokens / 1M) × target.input_per_mtok
+ (output_tokens / 1M) × target.output_per_mtok
+ (cache_read_tokens / 1M) × target.cache_read_per_mtok
+ (cache_write_tokens/ 1M) × target.cache_write_per_mtok
savings = current_model_cost − cost_at_target
Pull target.*_per_mtok from /api/pricing (longest model_pattern match wins). Default rates ($/Mtok in/out/cacheRead/cacheWrite): Opus $5/$25/$0.50/$6.25, Sonnet $3/$15/$0.30/$3.75, Haiku $1/$5/$0.10/$1.25.
Eligibility — don't promise savings on work that needs the big model
Re-pricing the full token mix is the theoretical ceiling. Scope it to eligible work:
- Low-turn sessions (
metadata.turn_countsmall) and simple subagent/tool work are safe to downshift. - Heavy-reasoning sessions (many thinking_blocks, high turn counts) likely need the premium model — exclude or discount them.
- Report both the full re-price (ceiling) and an eligible-only estimate, and state the eligibility rule you applied.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 13d ago First seen · 74 lines · 88 tokens per session scan A e026d2681777
model-savings is a skill published in the GitHub repository hoangsonww/Claude-Code-Agent-Monitor (991 stars, last pushed 3d ago), licensed MIT. It adds 88 tokens to every session and 995 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
code-remediate
Apply selected review fixes; bare PR targets use current online items, while PR +review adds the latest matching artifact.
nodejs-expert
Expert-level Node.js backend development with Express, async patterns, streams, performance optimization, and production best practices. Use when the user mentions JavaScript, backend, Express, or async, or when the task involves Modern Node.js Features, Express Framework, File System Operations, or HTTP Requests.
optimize
Optimize a measurable metric with bounded iterations, guardrails, and regression gates.
react-tanstack-router
Use when implementing routing in a React app (NOT Next.js) with TanStack Router — file-based routes, loaders, search params.
laravel-blade
Create Blade templates with components, slots, layouts, and directives. Use when building views, reusable components, or templating.
laravel-eloquent
Use when working with database models — Eloquent ORM, PHP attributes, relationships, queries, observers, or factories in Laravel 13.