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 agentproto/ts --skill ap-models-authgit clone --depth 1 https://github.com/agentproto/tsWrote 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/agentproto/ts/ap-models-auth)<a href="https://agentmods.dev/skills/agentproto/ts/ap-models-auth"><img src="https://agentmods.dev/badge/skills/agentproto/ts/ap-models-auth/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/agentproto/ts/ap-models-auth"><img src="https://agentmods.dev/badge/skills/agentproto/ts/ap-models-auth.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 | $0.00069 | $0.01046 |
| Opus 5.5 | $0.00028 | $0.00418 |
| Sonnet 5.5 | $0.00014 | $0.00209 |
| Haiku 4.5 | $0.00007 | $0.00105 |
Grade A, and why
ap-models-auth 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 — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ap-models-auth
When to use
- Before spawning: which models are actually runnable given the auth profiles on this host.
- A spawn is rejected or bills through the wrong wallet — check/curate profiles.
- "How much did we spend this week?" — rolling spend estimates.
Catalog: what is spawnable
// Spawnable routes, profile-aware runnable flags
catalog_models({ "adapter": "claude-code", "runnableOnly": true })
// → [{ "vendor": "z-ai", "product": "glm-5.2", "route": "openrouter", "runnable": true }, ...]
// Exhaustive per-provider list (for a picker UI)
catalog_provider_models({ "endpoint": "openrouter" })
Model identity is vendor/product with an optional @route for transport/billing — e.g. z-ai/glm-5.2@openrouter. The route is distinct from the product identity: the same product can exist on several routes with different cost/limits.
Auth profiles: named wallets
// What exists (non-secret metadata + keyStatus)
auth_profile_list({ "endpoint": "anthropic" })
// Import an existing credential discovered on this host (claude-code login, env vars, hermes config)
auth_discover_credentials({})
auth_profile_import({ "origin": "claude-code", "endpoint": "anthropic", "id": "anthropic-sub" })
// Create explicitly — the secret is stored, never echoed
auth_profile_create({ "id": "openrouter-env", "endpoint": "openrouter", "method": "api-key", "credential": "sk-or-..." })
// Curate: enable/disable; narrow to a model allowlist
auth_profile_set_enabled({ "id": "openrouter-env", "enabled": false })
auth_profile_set_models({ "id": "openrouter-env", "mode": "allow", "ids": ["z-ai/glm-5.2", "deepseek/deepseek-v4-pro"] })
Profiles are named — spawn with access: { "profileRef": "openrouter-env" } to bill through one. A disabled profile drops every model it would serve to non-runnable, immediately.
Harness presets: pin harness → profile + model
harness_preset_create({ "id": "hm-cheap", "harnessSlug": "hermes", "name": "Cheap",
"profileRef": "openrouter-env", "defaultModel": "z-ai/glm-5.2" })
harness_preset_list({ "harnessSlug": "hermes" })
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 First seen · 86 lines · 69 tokens per session scan A 413f8a9d3a8e
ap-models-auth is a skill published in the GitHub repository agentproto/ts (10 stars, last pushed yesterday), licensed Apache-2.0. It adds 69 tokens to every session and 1,046 once invoked, about $0.0003 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 2026-09-04.
Other skills, from other repositories
comparable-company-analysis
A workflow for comparing a publicly listed company with similar listed companies. It examines their businesses, financial results, competitors, and recent developments.
财经分析工具包
A set of finance analysis tools for stocks, markets, portfolios, and financial news. It includes data retrieval, technical indicators such as moving averages and RSI, trend analysis, risk assessment, and allocation suggestions.
meter-chargeback
CocoMeter chargeback and FinOps governance. Usage: $meter chargeback refresh | $meter chargeback invoice | $meter chargeback onboarding.
meter-estimate
Pre-flight token and cost estimation for a planned action. Analyzes the current plan or a described action and estimates token consumption, Snowflake credit usage, and whether it exceeds configured thresholds.
meter-invoice
Generate CocoMeter chargeback invoices. Usage: $meter invoice.
meter-refresh
Refresh CocoMeter chargeback facts. Usage: $meter refresh.