go-authcrunch: Skill for Codex

.codex/skills/authorization-policy-oauth/SKILL.md

authorization-policy-oauth is a skill for Codex from greenpau/go-authcrunch. It costs 59 tokens per session (2,141 once invoked), scanned A, original, Apache-2.0.

An authorization layer for adding OAuth login to policy-controlled applications without running a separate authentication portal. OAuth lets an application sign users in through an external identity provider.

In plain words
What is it for?
Use it to configure one OAuth identity provider, parse authorization directives, manage sessions, enforce access-control rules, and embed OAuth in a server.
Why use it?
It handles policy configuration, login sessions, access checks, logout, TLS end-to-end tests, and provider integration while leaving identity verification to the OAuth provider.

Skill for Codex

Written for Codex: agents/openai.yaml present.

This is greenpau/go-authcrunch's own configuration. It tells Codex how to work on go-authcrunch itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything go-authcrunch configures →

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is make test TEST_DIR='./pkg/authz/... . ./internal/tag' COVERAGE_DIR='.coverage/oauth-authorization'.

Reuse

Borrowing it

Nothing to install: this file belongs to greenpau/go-authcrunch. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/greenpau/go-authcrunch/main/.codex/skills/authorization-policy-oauth/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/greenpau/go-authcrunch

Made for: Codex.

Wrote 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.

agentmods badge for authorization-policy-oauth

README.md
[![agentmods](https://agentmods.dev/badge/skills/greenpau/go-authcrunch/authorization-policy-oauth/github.svg)](https://agentmods.dev/skills/greenpau/go-authcrunch/authorization-policy-oauth)
Your own site
<a href="https://agentmods.dev/skills/greenpau/go-authcrunch/authorization-policy-oauth"><img src="https://agentmods.dev/badge/skills/greenpau/go-authcrunch/authorization-policy-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.

agentmods 80×15 button for authorization-policy-oauth

Your own site · 80×15
<a href="https://agentmods.dev/skills/greenpau/go-authcrunch/authorization-policy-oauth"><img src="https://agentmods.dev/badge/skills/greenpau/go-authcrunch/authorization-policy-oauth.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 59 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,141 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00059 $0.02141
Opus 5.5 $0.00024 $0.00856
Sonnet 5.5 $0.00012 $0.00428
Haiku 4.5 $0.00006 $0.00214

Measured 17d ago against content hash fd145a9a9239, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

authorization-policy-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 17d 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.

.codex/skills/authorization-policy-oauth/SKILL.md · 178 lines

How it starts

The opening of the file, as written. The whole thing — 178 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Authorization Policy OAuth

Read external account attachments when changing local provisioning, connection UI, immutable external keys, or attachment binding in this consumer.

Ownership and public API

pkg/authz/oauth_config.go owns OAuthAuthorizationConfig, its defaults and validation, and PolicyConfig.ConfigureOAuth. The serialized field is PolicyConfig.OAuth (oauth). pkg/authz/oauth/parser exposes NewOAuthAuthorizationConfigFromDirectives(policyName, statements) for complete encoded statements. Empty input disables the feature; nonempty input requires exactly one use oauth identity provider NAME. Apply the returned snapshot with ConfigureOAuth; other policy settings and ACL rules remain independent.

pkg/authz/oauth.go owns HTTP orchestration and bounded session state. pkg/authz/oauth_state.go integrates opt-in runtime-state persistence for completed sessions; unfinished upstream transactions stay volatile. authz.NewGatekeeperWithIdentityProviders(config, providers, logger) selects a configured shared OAuth provider. NewGatekeeper remains compatible for ordinary JWT policies and rejects OAuth configuration without a provider. The root NewServer passes its shared providers; NewServerWithOptions can inject their upstream login store. That injection does not share this policy's pending logins or opaque sessions; affinity is still required for direct-policy journeys. No portal or configured identity store is needed. Direct providers must also expose CancelLogin(string, [32]byte, string) bool; the built-in OAuth provider implements it without changing idp.IdentityProvider. Root validation rejects missing, disabled, wrong-kind and ambiguous references, overlapping OAuth endpoint namespaces, and cookie collisions between policies.

Read configuration and operation for exact grammar, transport semantics, deployment constraints, and examples. Hosts must adapt their configuration syntax and preserve all three authentication outcomes: Authorized/Bypassed permits downstream execution; an error denies access; otherwise the gatekeeper handled the response and the host must preserve it without invoking downstream handlers. Parser availability alone does not enable host configuration syntax. Do not modify or run tooling in sibling repositories during work here.

Read the full file on GitHub · 178 lines

Files

What ships with it

2 files 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.

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. 17d ago Changed · +17 lines fd145a9a9239
  2. 29d ago Changed · +3 lines 16d9c5217637
  3. 1mo ago Changed · +2 lines 155b56d6fa24
  4. 1mo ago First seen · 156 lines · 59 tokens per session scan A b73e8c8c6ddb

Subscribe to this mod's changes

authorization-policy-oauth is a skill published in the GitHub repository greenpau/go-authcrunch (60 stars, last pushed 10d ago), licensed Apache-2.0. It adds 59 tokens to every session and 2,141 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 2026-09-21.

Related

authorization-policy-oauth compared with skills from other repositories

authorization-policy-oauth next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
authorization-policy-oauthgreenpau/go-authcrunchSkill6010d agoApache-2.0A59Codex
mem0-oss-to-platformmem0ai/mem0Skill68k2d agoApache-2.0A217Claude Code, Codex
azure-mgmt-botservice-dotnetmicrosoft/skillsSkill3.2kyesterdayMITA78Claude Code
fastapi-router-pymicrosoft/skillsSkill3.2kyesterdayMITA46Claude Code
dev-runtimelangwatch/langwatchSkill5.0kyesterdayApache-2.0A172Claude Code
api-designericrisco/rsc-harnessSkill5032d agoMITA105Claude Code, Codex
migrate-segw-to-raparc-mcp/arc-1Skill252yesterdayMITA106Claude Code