auth

A skill for giving agents or connected services securely managed credentials, such as API keys or Bearer authentication tokens.

In plain words
What is it for?
Use it when an agent or connected MCP service must call a remote API, with credentials stored once and applied to requests at connection or call time.
Why use it?
It keeps secrets in a credential store instead of exposing them through shared environment variables or hardcoded configuration, and resolves fresh authorization headers when needed.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/agentproto/ts/auth
Any agent
npx skills add agentproto/ts --skill auth
Clone the repo
git clone --depth 1 https://github.com/agentproto/ts

Made for: Claude Code, Codex.

Per session 92 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,711 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00092 $0.01711
Opus 5 $0.00046 $0.00856
Sonnet 5 $0.00018 $0.00342
Haiku 4.5 $0.00009 $0.00171

Measured yesterday against content hash 025a9bedf774, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 yesterday.

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.

packages/skill-pack-agentpush/src/skills/auth/SKILL.md · 140 lines

How it starts

The opening of the file, as written. The whole thing — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.

When to use

Reach for this whenever an agent (or a child MCP it mounts) must present a credential to a remote service and you don't want that secret sprayed into the daemon's global env or hardcoded in a config file. The hallmark: "how do I give this agent access to <service> without leaking the key to every other agent?"

  • A tool/agent calls a Bearer API (agentpush, Stripe, an internal API).
  • A hosted/remote MCP server needs an Authorization header.
  • You want ONE place to store a key, scoped per service, resolved fresh (with refresh) at use-time instead of a long-lived env var.

Do NOT use for the daemon's own tunnel login (that's agentproto auth login, a device-code flow already wired) — though it uses the same substrate underneath.

The model — one source of truth, resolved on demand

auth provider (declares WHERE/HOW)  ──┐
CredentialStore (holds the secret)  ──┤─▶ CredentialBroker.resolveHeaders({ path, audience })
                                       │        → { Authorization: "Bearer …" }  (fresh, per call)
  • Provider — a manifest declaring a service's id, apiBase, and auth flow. Config only, never the secret. Registered once (registerAuthProvider).
  • CredentialStore — where the secret lives: KeychainStore (macOS CLI), FileStore (AES-256-GCM, headless — key from AGENTPROTO_STORE_KEY), MemoryStore (tests). Swap the backend, same interface.
  • BrokerresolveHeaders({ path, audience?, signal? }) turns a provider path into ready-to-use headers: serves a fresh stored bearer, else runs the flow. audience (api / mcp / tunnel) scopes the credential so it can't be reused cross-plane.
  • Flows — pick one per service: pat (static token you store/paste), service-auth (auth.md claim ceremony → short oat + durable assertion), device-code (RFC 8628 → durable daemon token + refresh).

Recipe

1. Declare + register the provider

TS literal (builtin/tests):

import { defineAuthProvider, registerAuthProvider } from "@agentproto/auth"

registerAuthProvider(defineAuthProvider({
  id: "agentpush",
  description: "AgentPush API — paste a personal API key.",
  apiBase: "https://api.agentpush.example",
  audience: "mcp",                       // or "api"
  auth: { flow: "pat", tokenStore: { keychain: "agentpush", account: "{server}" } },
}))

Or ship a vendor *.auth.md and parseAuthProviderManifest(...)registerAuthProvider(...) — a host adds providers without editing this package.

Read the full file on GitHub · 140 lines

Changes

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.

  1. yesterday First seen · 140 lines · 92 tokens per session scan A 025a9bedf774

Subscribe to this mod's changes

auth is a skill published in the GitHub repository agentproto/ts (5 stars, last pushed 2d ago), licensed Apache-2.0. It adds 92 tokens to every session and 1,711 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 2026-08-31.

Related

Other skills, from other repositories

strands-review

Local preview of the strands-agents/devtools /strands review agent. Body is the upstream Task Reviewer SOP verbatim — do not paraphrase. Use when the user types /strands-review, asks for a "strands review" of a PR, or wants to anticipate what the remote /strands review GitHub Action will flag. Findings are close but…

strands-agents/harness-sdk · 125 tokens

docs-writer

Draft or rewrite Strands Agents documentation pages. Use when writing new doc pages, rewriting pages that failed audit, drafting sections for existing pages, or writing blog posts and release notes about Strands. Also triggers on "write a doc", "draft a page", "rewrite the quickstart", "add a tutorial for X"…

strands-agents/harness-sdk · 74 tokens

pr-create

Creates a GitHub pull request using the gh CLI. Use when the user asks to create, open, or submit a PR on GitHub.

strands-agents/harness-sdk · 32 tokens

document-service

This skill should be used when the user asks to "analyze this codebase", "document this service", "generate technical docs", "I inherited this code", "help me understand this system", "create docs for this project", "what does this system look like", "onboard me to this codebase", "this codebase has no docs"…

awslabs/agent-plugins · 141 tokens

aws-step-functions

Build workflows with AWS Step Functions state machines using the JSONata query language. Covers Amazon States Language (ASL) structure, state types, variables, data transformation, error handling, AWS service integration, and migrating from the JSONPath to the JSONata query language.

awslabs/agent-plugins · 57 tokens

hyperpod-version-checker

Check and compare software component versions on SageMaker HyperPod cluster nodes - NVIDIA drivers, CUDA toolkit, cuDNN, NCCL, EFA, AWS OFI NCCL, GDRCopy, MPI, Neuron SDK (Trainium/Inferentia), Python, and PyTorch. Use when checking component versions, verifying CUDA/driver compatibility, detecting version mismatches…

awslabs/agent-plugins · 120 tokens