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 vinilana/invokta --skill maintain-mcp-oauthgit clone --depth 1 https://github.com/vinilana/invoktaWrote 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/vinilana/invokta/maintain-mcp-oauth)<a href="https://agentmods.dev/skills/vinilana/invokta/maintain-mcp-oauth"><img src="https://agentmods.dev/badge/skills/vinilana/invokta/maintain-mcp-oauth/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/vinilana/invokta/maintain-mcp-oauth"><img src="https://agentmods.dev/badge/skills/vinilana/invokta/maintain-mcp-oauth.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Privilege Escalation · line 22 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
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 | $0.00099 | $0.00687 |
| Opus 5 | $0.00049 | $0.00344 |
| Sonnet 5 | $0.00020 | $0.00137 |
| Haiku 4.5 | $0.00010 | $0.00069 |
Grade A, and why
maintain-mcp-oauth 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.
How it starts
The opening of the file, as written. The whole thing — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Maintain MCP OAuth
Resolve the project root as three directories above this SKILL.md. Perform
all relative reads and commands from that root; do not diagnose a neighboring
project merely because it is the caller's current working directory.
Build evidence first
- Read
AGENTS.md,docs/OAUTH_ARCHITECTURE.md, anddocs/OAUTH_TROUBLESHOOTING.mdcompletely. - Read the affected source and tests under
src/oauth,src/http-auth.ts,src/oauth-server.ts,test/oauth-provider.test.ts,test/oauth-server.test.ts, andtest/http-auth.test.ts. - Separate the browser interaction, authorization endpoint, callback, token exchange, and MCP request into distinct stages.
- Use sanitized logs and artifact counts or non-secret metadata. Never print passwords, cookie values, client secrets, registration access tokens, authorization codes, PKCE verifiers, state, or interaction IDs.
Diagnose safely
- Probe discovery, protected-resource metadata, and JWKS without credentials.
- Use
npm run oauth:probe-dcr -- --url ORIGINfor DCR; it removes its client. - Use only a callback on a controlled origin for automated browser-flow tests.
- Do not use the owner's credentials to authorize a client with an external callback unless the user explicitly approves that sensitive flow.
- Treat an authorization code with no
/tokenrequest as a callback/client problem, not a password or consent persistence problem. - Treat a second submit on the same interaction as stale; diagnose the first submit instead of weakening interaction replay protection.
Preserve invariants
- Keep Authorization Code and mandatory S256 PKCE.
- Keep DCR defaults on ES256 and a confidential client authentication method.
- Continue accepting explicitly registered
client_secret_postclients. - Validate access-token signature, issuer, audience, subject, and
mcp:tools. - Keep refresh-token rotation and bounded token lifetimes.
- Keep the single-owner model without public registration.
- Limit consent redirect chains to HTTPS or exact HTTP loopback callbacks.
- Keep authentication fail-closed during metadata, JWKS, or database failure.
- Persist users, keys, clients, grants, sessions, and tokens together.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 61 lines · 99 tokens per session scan A eb354ac51d12
maintain-mcp-oauth is a skill published in the GitHub repository vinilana/invokta (129 stars, last pushed yesterday), licensed MIT. It adds 99 tokens to every session and 687 once invoked, about $0.0005 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
mem0-oss-to-platform
Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…
agui-dotnet-protobuf
Use the protobuf wire transport (instead of the default Server-Sent Events) for an AG-UI connection with the AG-UI .NET SDK — a compact binary event stream negotiated via the Accept header. USE FOR: making an AGUIChatClient prefer protobuf by wiring an AGUIEventStreamHandler with ProtobufEventStreamFormatter (then…
azure-mgmt-botservice-dotnet
Azure Resource Manager SDK for Bot Service in .NET. Management plane operations for creating and managing Azure Bot resources, channels (Teams, DirectLine, Slack), and connection settings. Triggers: "Bot Service", "BotResource", "Azure Bot", "DirectLine channel", "Teams channel", "bot management .NET", "create bot".
fastapi-router-py
Create FastAPI routers with CRUD operations, authentication dependencies, and proper response models. Use when building REST API endpoints, creating new routes, implementing CRUD operations, or adding authenticated endpoints in FastAPI applications.
migrate-segw-to-rap
Reverse-engineer a SEGW-built OData V2 service (MPC/DPC/MPCEXT/DPCEXT) into a modern RAP V4 service — tables, CDS views (interface + projection), behavior definitions, draft entities, service definition + binding. Use when asked to "migrate this SEGW service to RAP", "convert OData V2 to V4 RAP", "modernize this…
telnyx-messaging-hosted-curl
Set up hosted SMS numbers, toll-free verification, and RCS messaging. Use when migrating numbers or enabling rich messaging features. This skill provides REST API (curl) examples.