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 attentiondotnet/davidondrej-skills --skill pi-custom-modelgit clone --depth 1 https://github.com/attentiondotnet/davidondrej-skillsWrote 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/attentiondotnet/davidondrej-skills/pi-custom-model)<a href="https://agentmods.dev/skills/attentiondotnet/davidondrej-skills/pi-custom-model"><img src="https://agentmods.dev/badge/skills/attentiondotnet/davidondrej-skills/pi-custom-model/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/attentiondotnet/davidondrej-skills/pi-custom-model"><img src="https://agentmods.dev/badge/skills/attentiondotnet/davidondrej-skills/pi-custom-model.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 | $0.00116 | $0.01018 |
| Opus 5 | $0.00058 | $0.00509 |
| Sonnet 5 | $0.00023 | $0.00204 |
| Haiku 4.5 | $0.00012 | $0.00102 |
Grade A, and why
pi-custom-model 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 11d 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.
This is a copy
100% identical to pi-custom-model — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pi custom / variant model
When to use
Pi's saved default only loads if the exact provider/id exists in its model registry. Pi ships a static bundled list per provider — so OpenRouter routing-shortcut variants (:nitro = sort by throughput, :floor = cheapest, :exacto = quality tool-use) and any brand-new slug are NOT in it. When the default doesn't resolve, Pi silently falls through to its built-in per-provider default (for openrouter that's moonshotai/kimi-k2.6) — looking like Pi "reset" your model. Fix = register the slug as a custom model so find(provider, id) matches.
Files (global)
~/.pi/agent/settings.json—defaultProvider,defaultModel,defaultThinkingLevel~/.pi/agent/models.json— custom models, keyed by provider~/.pi/agent/auth.json— provider credentials (check the provider key exists)
Steps
- Confirm the slug is real before adding it (e.g. check the OpenRouter model/variant exists). A typo'd id also silently falls back.
- Confirm auth. The provider must have a key in
auth.json(or an env var likeOPENROUTER_API_KEY). No auth → the model is registered but unavailable → still falls back. - Add the model to
models.jsonunderproviders.<provider>.models. For a built-in provider (openrouter, anthropic, etc.) you only supply metadata —api,baseUrl, and auth are inherited from the bundled defaults. Example:
Copy{ "providers": { "openrouter": { "models": [ { "id": "z-ai/glm-5.2:nitro", "name": "Z.ai: GLM 5.2 (nitro)", "reasoning": true, "thinkingLevelMap": { "xhigh": "xhigh" }, "input": ["text"], "cost": { "input": 0.95, "output": 3, "cacheRead": 0.18, "cacheWrite": 0 }, "contextWindow": 1048576, "maxTokens": 32768, "compat": { "supportsDeveloperRole": false, "thinkingFormat": "openrouter" } } ] } } }cost/contextWindow/compatfrom the base model (the variant shares them) — find the bundled entry in<pi-pkg>/node_modules/@earendil-works/pi-ai/dist/providers/<provider>.models.js. Don't hardcode generic 128k/16k if the real model is bigger. - Set the default in
settings.json:defaultProvider+defaultModel= the exact id. LeavedefaultThinkingLevelas the user has it. - Verify:
pi --list-models | grep <id>shows it, and JSON parses. Optionally smoke-test:pi --provider <p> --model "<id>" "which model are you?".
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.
- 11d ago First seen · 53 lines · 116 tokens per session scan A a0e0a7090a62
pi-custom-model is a skill published in the GitHub repository attentiondotnet/davidondrej-skills (11 stars, last pushed 2mo ago), licensed MIT. It adds 116 tokens to every session and 1,018 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to pi-custom-model, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…