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 rcarmo/piclaw-addons --skill cheapskategit clone --depth 1 https://github.com/rcarmo/piclaw-addonsWrote 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/rcarmo/piclaw-addons/cheapskate)<a href="https://agentmods.dev/skills/rcarmo/piclaw-addons/cheapskate"><img src="https://agentmods.dev/badge/skills/rcarmo/piclaw-addons/cheapskate/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/rcarmo/piclaw-addons/cheapskate"><img src="https://agentmods.dev/badge/skills/rcarmo/piclaw-addons/cheapskate.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 | $0.00029 | $0.00615 |
| Opus 5.5 | $0.00012 | $0.00246 |
| Sonnet 5.5 | $0.00006 | $0.00123 |
| Haiku 4.5 | $0.00003 | $0.00061 |
Grade A, and why
cheapskate 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 1mo 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 — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cheapskate
Select cheapskate/auto from the model picker to route through explicitly enabled models whose effective Piclaw/Pi catalogue costs are all exactly zero.
Eligibility
A physical model is eligible only when:
- the effective catalogue contains it;
- input, output, cache-read and cache-write base rates are finite zero values;
- every optional price tier also has four finite zero rates;
- its provider has configured authentication and the model is currently available;
- Settings enables the provider and model;
- the current session model scope permits it;
- its input, context and output capabilities fit the request;
- it has no active health quarantine or cooldown.
Positive, missing, malformed and unknown price metadata fails closed. A models.json model that omits cost remains unknown even when Pi normalises its displayed rates to zero. Trial credit and provider marketing do not make a positive-price model eligible. Newly discovered zero-cost models are disabled until the user enables them.
Identity
The session model remains:
cheapskate/auto
The final assistant message records the physical provider/model in responseModel and in a cheapskate.route diagnostic. Use those fields when reporting which route handled a request.
Settings
Open Settings → Cheapskate to:
- filter exact-zero candidates by text or provider;
- inspect catalogue-derived context, output, reasoning and image support;
- enable or disable models;
- set route priority;
- view active route, health, cooldown and last error;
- see why the virtual model is unavailable.
Configure provider credentials through Piclaw's normal login/keychain flow. The pane does not maintain its own credential catalogue.
Failover
Cheapskate tries at most three physical routes. It may retry a transient failure only before text, thinking or tool-call output has been emitted. It never replays after output begins because that can duplicate content or tool effects.
The router respects provider Retry-After and recognised rate-limit reset headers. It uses a bounded fallback cooldown when headers are absent. Route preference is session-local and concurrent chats retain request-local attribution.
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.
- 1mo ago Changed · -6 lines · -3 tokens per session f73d78c792da
- 2mo ago First seen · 71 lines · 32 tokens per session scan A 5bb22e482194
cheapskate is a skill published in the GitHub repository rcarmo/piclaw-addons (23 stars, last pushed yesterday), licensed MIT. It adds 29 tokens to every session and 615 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 2026-08-30.
Other skills, from other repositories
pi
Use when you need a minimal, extensible terminal AI coding agent harness in TypeScript — npm @earendil-works/pi-coding-agent 1.4.0, extensions/skills/prompt templates, multi-provider (OpenAI/Anthropic/Google) routing, container isolation (Docker/Gondolin/OpenShell); also for pi: command not found, Node >=22.19.0…
OpenShell + Pi: build an isolated coding-agent sandbox
Use when the user wants to install, configure, migrate, harden, inspect, or troubleshoot a Pi coding agent running in NVIDIA OpenShell, especially with rootless Podman, deny-by-default networking, hidden credentials, persistent state, or A2A communication. Do not use for ordinary containerization that does not involve…
ensembl-database
Query Ensembl genome database REST API for 250+ species. Gene lookups, sequence retrieval, variant analysis, comparative genomics, orthologs, VEP predictions, for genomic research.
ai-music
A workflow that turns a topic or script into a finished short video by combining writing, images or video clips, spoken narration, subtitles, background music, and final assembly.
skill-news-intelligence
A daily industry-news research workflow that gathers in-depth articles and updates from Chinese technology, business, creator, and AI publications. It filters the results by a creator’s field and turns them into a brief with possible content topics.
sidewinder-rattlesnake
Adversary-emulation profile for SideWinder (G0121 / Rattlesnake / T-APT-04 / Razor Tiger), India's suspected state-sponsored cyber-espionage actor.