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 kunchenguid/quota-axi --skill provider-adaptersgit clone --depth 1 https://github.com/kunchenguid/quota-axiWrote 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/kunchenguid/quota-axi/provider-adapters)<a href="https://agentmods.dev/skills/kunchenguid/quota-axi/provider-adapters"><img src="https://agentmods.dev/badge/skills/kunchenguid/quota-axi/provider-adapters/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/kunchenguid/quota-axi/provider-adapters"><img src="https://agentmods.dev/badge/skills/kunchenguid/quota-axi/provider-adapters.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 | $0.00041 | $0.04078 |
| Opus 5.5 | $0.00016 | $0.01631 |
| Sonnet 5.5 | $0.00008 | $0.00816 |
| Haiku 4.5 | $0.00004 | $0.00408 |
Grade A, and why
provider-adapters 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 10d 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 — 192 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Provider Adapters & Quirks
This reference details the credential sources, endpoint contracts, quota window structures, error handling, and vendor-specific quirks for the providers with dedicated sections below. Muse has no section here; its specification lives in the README provider notes.
1. Anthropic Claude (claude)
- Credential Sources (evaluated in order):
env(CLAUDE_CODE_OAUTH_TOKEN): Takes top precedence because Claude Code resolves environment tokens before opening local stores. It has noexpiresAtor refresh token; never invent either and never route it through delegated refresh.claudeEnvOauthTokeninsrc/lib/claude-profile.tsis the single reader.claudeCredentialContextIdincludes an env marker to prevent serving stored-credential cache snapshots for environment sessions.oauth-file: Reads the local profile credentials file.keychain: macOS Keychain item matching Claude Code's validated user account selector. Ambiguous service-only queries are forbidden. Value reads require an existing non-secret access marker (0600) or--allow-keychain-prompt. Keychain failures (including exit 44) must never retire the cache.
- Quota Windows:
- Windows can include
five_hour,seven_day,seven_day_opus, andextra_usage. - When the OAuth usage payload includes a
limitsarray, that array is authoritative over top-level fields. It exposes active limits, including model-scoped limits (e.g. Fable) viascope.model.display_name, assigned window IDmodel:<slug>.
- Windows can include
- Soft Expiry: A stored-expired, refreshable Claude token definitively rejected by the endpoint produces
authStatus: expired_refreshable(a soft failure retaining cache), neverauth_required. - Native Quota Probe: Bounded opt-in native inference quota probe lives in
src/providers/claude-native-quota.ts. Keep it distinct from delegated refresh. - Delegated Refresh: Permitted via
claude doctoronly when no Claude Code process is running (src/lib/running-processes.ts).
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.
- 10d ago Changed · +1 lines e6acb900763e
- 12d ago Changed 78bb954bc824
- 13d ago First seen · 191 lines · 41 tokens per session scan A 9f6538d46dbb
provider-adapters is a skill published in the GitHub repository kunchenguid/quota-axi (155 stars, last pushed yesterday), licensed MIT. It adds 41 tokens to every session and 4,078 once invoked, about $0.0002 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 2026-10-05.
Other skills, from other repositories
api-integration-architect
Design, implement, debug, and optimize API integrations with expert-level patterns for REST, GraphQL, webhooks, and authentication flows.
printing-press-amend
Amend a published CLI from one of two input sources: (1) dogfood mode mines the active Claude Code session transcript for friction (missing flags, hand- rolled API payloads, silent-null returns); (2) direct-input mode accepts user-supplied asks (rename a command, add commands or feeds, fix a named bug, optionally…
convex-performance-audit
Audits Convex performance for reads, subscriptions, write contention, and function limits. Use for slow features, insights findings, OCC conflicts, or read amplification.
convex-insights
Query a running Convex app's logs + health in natural language (official MCP): failures, slow/expensive functions, deploy causality — scoped, evidence-backed, with a dashboard deep link.
diagnose-backend-bug
Diagnose a bounded backend or multi-service failure from GitHub Issues, Jira, Aone, user-provided exports, logs, traces, responses, stack traces, or job records. Use when a service, API, RPC, worker, queue, CLI, or scheduled job bug needs correlation through the project's existing observability route before repair; do…
axiom-networking
Use when implementing or debugging ANY network connection, API call, or socket in an Apple app. Covers URLSession, Network.framework, NetworkConnection, connection diagnostics.