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.
curl -O https://raw.githubusercontent.com/greenpau/go-authcrunch/main/.codex/skills/external-authorization/SKILL.mdgit clone --depth 1 https://github.com/greenpau/go-authcrunchWrote 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/greenpau/go-authcrunch/external-authorization)<a href="https://agentmods.dev/skills/greenpau/go-authcrunch/external-authorization"><img src="https://agentmods.dev/badge/skills/greenpau/go-authcrunch/external-authorization/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/greenpau/go-authcrunch/external-authorization"><img src="https://agentmods.dev/badge/skills/greenpau/go-authcrunch/external-authorization.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 | $0.02112 |
| Opus 5.5 | $0.00016 | $0.00845 |
| Sonnet 5.5 | $0.00008 | $0.00422 |
| Haiku 4.5 | $0.00004 | $0.00211 |
Grade A, and why
external-authorization 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 29d 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 — 204 lines — stays where its author put it; the contents beside it link to each section on GitHub.
External Authorization
Ownership and integration
pkg/authz/external owns the public Backend.Decide(context.Context, Request) (*Result, error) interface, identity/policy binding, bounded request snapshots,
and Authorizer. plugins/external-authorization/httpjson implements the HTTP
transport. Core production packages must not import the plugin.
An embedding host parses both configurations, constructs httpjson.New(config, client), constructs external.New(binding, backend), and calls
Gatekeeper.SetExternalAuthorizer or TokenValidator.SetExternalAuthorizer
before serving. Nil/unconstructed gatekeepers and closed validators reject
attachment without panic. An invalid/nil attachment cannot disable enforcement.
Hosts own backend lifetime and must drain requests before replacement or disposal.
There is no root JSON plugin loader, process-global registry, or automatic host
module registration. The runtime hook is opt-in; omitted attachment preserves
existing authorization behavior.
Local credential verification, source/path restrictions, enrichment and every
local ACL check must pass before consulting the backend. An external allow is
an additional requirement and cannot override local denial. Enforcement covers
fresh JWTs, authentication-cache hits, Basic/API-key authentication and
AuthorizeUser, including OAuth callback admission and existing OAuth sessions.
AuthorizeUser and Authorizer.Authorize require an already authenticated
identity; neither authenticates arbitrary caller claims.
Explicit bypass routes retain their existing behavior and do not invoke the
backend. OAuth protocol endpoints retain their separate admission rules. Denial,
transport/protocol failure and cancellation map to ErrAccessNotAllowed through
the validator, using the existing forbidden response (normally HTTP 403, or a
configured forbidden redirect), without disclosing service details or clearing
valid credentials merely because the service denied access.
Policy configuration
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.
- 29d ago First seen · 204 lines · 41 tokens per session scan A 3d56691e53ba
external-authorization is a skill published in the GitHub repository greenpau/go-authcrunch (60 stars, last pushed 10d ago), licensed Apache-2.0. It adds 41 tokens to every session and 2,112 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 2026-10-08.
external-authorization compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| external-authorizationgreenpau/go-authcrunch | Skill | 60 | 10d ago | Apache-2.0 | A | 41 | Codex |
| mem0-oss-to-platformmem0ai/mem0 | Skill | 68k | 2d ago | Apache-2.0 | A | 217 | Claude Code, Codex |
| azure-mgmt-botservice-dotnetmicrosoft/skills | Skill | 3.2k | yesterday | MIT | A | 78 | Claude Code |
| fastapi-router-pymicrosoft/skills | Skill | 3.2k | yesterday | MIT | A | 46 | Claude Code |
| dev-runtimelangwatch/langwatch | Skill | 5.0k | yesterday | Apache-2.0 | A | 172 | Claude Code |
| api-designericrisco/rsc-harness | Skill | 503 | 2d ago | MIT | A | 105 | Claude Code, Codex |
| migrate-segw-to-raparc-mcp/arc-1 | Skill | 252 | yesterday | MIT | A | 106 | Claude Code |