Page Agent is a JavaScript library that embeds a natural-language agent inside a web page and lets it operate the page through its text-based DOM. It is used for web copilots, form filling, accessibility, and browser workflows, while the catalogue entries provide agent skills and instructions for using it.
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 agentmods add skills/alibaba/page-agent/maintain-model-listnpx skills add alibaba/page-agent --skill maintain-model-listgit clone --depth 1 https://github.com/alibaba/page-agentWrote 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/alibaba/page-agent/maintain-model-list)<a href="https://agentmods.dev/skills/alibaba/page-agent/maintain-model-list"><img src="https://agentmods.dev/badge/skills/alibaba/page-agent/maintain-model-list.svg" alt="Measured on agentmods" 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 | $0.00053 | $0.01191 |
| Opus 5 | $0.00026 | $0.00596 |
| Sonnet 5 | $0.00011 | $0.00238 |
| Haiku 4.5 | $0.00005 | $0.00119 |
Grade A, and why
maintain-model-list 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 6d 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 — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Maintain Model List
The supported model list lives in three places that must stay in sync:
| File | What it holds |
|---|---|
packages/website/src/pages/docs/features/models/page.tsx |
MODEL_GROUPS (public docs, source of truth for display names) and BASELINE (recommended models) |
packages/llms/src/models.live.test.ts |
Mirrored MODEL_GROUPS, plus OPENROUTER_ID_OVERRIDES / ALIYUN_ID_OVERRIDES for provider-specific model ids |
packages/llms/src/utils.ts |
modelPatch — per-model-family request parameter fixes (thinking/reasoning flags, tool_choice quirks, etc.) |
Before Touching Anything
- Run
git status. If the working tree has uncommitted changes that look like unrelated in-progress work, do NOT edit files — report the situation and ask the user for permission first. - Run the full live test suite as a baseline:
npm run test:live -w @page-agent/llms. API keys come from the repo-root.env(TESTING_OPENROUTER_KEY,TESTING_ALIYUN_KEY,TESTING_DEEPSEEK_KEY); tests skip silently when a key is missing, so check which providers actually ran. Record which models pass/fail before making changes, so new failures are attributable.
Workflow A: A Specific Model Was Given
- Research the model (web search + provider docs):
- Is it served on OpenRouter? Fetch
https://openrouter.ai/api/v1/modelsand find the exact id (<vendor-slug>/<model-id>, watch for-preview, dated snapshots, dots vs hyphens). - Which other channels serve it (vendor native API, Aliyun DashScope, etc.) and what are their native model ids?
- API differences: can thinking/reasoning be disabled or minimized? Any
tool_choice,parallel_tool_calls, or parameter-schema quirks? Does the vendor's OpenAI-compatible endpoint differ from OpenRouter's behavior? - Agent suitability: tool call support is mandatory; note context window, latency, and cost.
- Is it served on OpenRouter? Fetch
- Update
modelPatchinpackages/llms/src/utils.tsif the model needs new parameter handling. Model names are matched afternormalizeModelName(lowercased,/-prefix,.and_stripped) — check whether an existing family branch already covers it. - Add the model to both
MODEL_GROUPSlists (website page and live test), newest first within its brand group. Add id overrides if the OpenRouter/Aliyun id differs from the display name. - Test availability carefully. Run the live suite and confirm the new model passes on every provider that serves it:
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.
- 6d ago First seen · 63 lines · 53 tokens per session scan A 74c8cc89d88f
maintain-model-list is a skill published in the GitHub repository alibaba/page-agent (28,995 stars, last pushed today), licensed MIT. It adds 53 tokens to every session and 1,191 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 2026-08-30.
Other skills, from other repositories
ab-testing
When the user wants to plan, design, or implement an A/B test or experiment, or build a growth experimentation program. Also use when the user mentions "A/B test," "split test," "experiment," "test th.
angular-developer
Generates Angular code and provides architectural guidance. Trigger when creating projects, components, services, or HTTP communication, or for best practices on reactivity (signals, linkedSignal, resource, httpResource), forms, dependency injection, routing, SSR, accessibility (ARIA), animations, styling (component…
reference-core
Explains the mental model and architecture of the code under packages/core. You MUST use this skill any time you plan to work with code in packages/core.
llm-redteam-overview
LLM red team category — full AATMF v3 tactic coverage (T01–T15). Routing skill: read this first to identify which tactic applies, then load the matching sub-skill. Maps to MITRE ATLAS where overlap exists.
vector-and-embedding-weaknesses
Hunt vector / embedding weaknesses (OWASP LLM08:2025) — adversarial inputs against the RAG / similarity layer that cause cross-tenant leak, embedding-inversion privacy loss, semantic confusion, and retriever-driven prompt injection.
shap
Model interpretability and explainability using SHAP (SHapley Additive exPlanations). Use this skill when explaining machine learning model predictions, computing feature importance, generating SHAP plots (waterfall, beeswarm, bar, scatter, force, heatmap), debugging models, analyzing model bias or fairness, comparing…