go-authcrunch: Skill for Codex

.codex/skills/authentication-client/SKILL.md

authentication-client is a skill for Codex from greenpau/go-authcrunch. It costs 49 tokens per session (2,532 once invoked), scanned A, original, Apache-2.0.

A reusable Go package for logging in to an authentication portal and handling passwords, one-time codes, API keys, and saved credential files. A one-time code, often called TOTP, is a short code generated by an authenticator app.

In plain words
What is it for?
Use it when embedding portal login in another Go application, changing password or TOTP challenges, supporting API keys, managing credential files, or testing login against a real portal.
Why use it?
It lets different command-line programs share the login protocol without mixing authentication with command parsing, terminal prompts, or application-specific configuration.

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/authclient/... ./cmd/authdbctl'.

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/authentication-client/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 authentication-client

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/greenpau/go-authcrunch/authentication-client"><img src="https://agentmods.dev/badge/skills/greenpau/go-authcrunch/authentication-client.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 49 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,532 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 $0.00049 $0.02532
Opus 5.5 $0.00020 $0.01013
Sonnet 5.5 $0.00010 $0.00506
Haiku 4.5 $0.00005 $0.00253

Measured 12d ago against content hash b1bf6fedaa86, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

authentication-client 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 12d 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/authentication-client/SKILL.md · 193 lines

How it starts

The opening of the file, as written. The whole thing — 193 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Authentication Client

Ownership

pkg/authclient is the importable consumer of pkg/apiauth JSON login types. It owns Config, Client, Options, PromptFunc, Credentials, and FileTokenStore. It sends only POST <base_url>/login; authentication does not require enable admin api. Keep server handlers in pkg/authn and management operations in cmd/authdbctl.

Read references/integration.md when embedding the client, choosing credential paths, or changing the CLI adapter. Public contracts also live beside the exported Go declarations and in pkg/authclient/doc.go.

The reusable package does not discover config, select application directories, read terminal input, log credentials, or dispatch CLI commands. Do not add urfave/cli, term, or application-name defaults to it. Applications own prompt presentation, config loading, user-agent identity, and credential persistence.

Protocol Invariants

  • NewClient validates a copy of configuration. Authenticate(ctx) starts a fresh exchange, returns credentials, and has no token-file side effects.
  • Keep each response newly decoded. Missing sandbox fields must not inherit previous response values. Continue only with a sandbox ID, sandbox secret, and next challenge; success requires a nonempty usable access token.
  • Keep the ten-request bound, response-size limit, context propagation, and refusal to follow redirects, including with an injected HTTP client.
  • Configured password/TOTP values avoid input prompts. PromptMFA returns totp or webauthn; the CLI translates numbered choices. Without a prompt, a configured TOTP secret can answer a combined MFA challenge directly.
  • APIKey selects a separate, single-request login with Realm; reject mixed username/password/TOTP configuration. Send the key only in the JSON body, never in the URL. Do not fall back to challenges or prompt after key rejection. The portal derives the identity using its existing proxy API key verifier. Keys are independent credentials, including for accounts enrolled in MFA. They do not satisfy password/TOTP/WebAuthn checkpoints; configured challenge requirements or an explicit saved flow preference can therefore deny key login. Key login issues an access token only, sets no cookies, and cannot create a refresh family. refresh_transport: body is rejected for this mode.
  • TOTP uses raw secret bytes and SHA-1, matching identity.MfaToken and existing authdbctl config. Do not silently interpret the secret as base32. Defaults are six digits and thirty seconds; accepted digits match the portal's four-to-eight range and the period must be positive.
  • U2F/WebAuthn assertion handling remains unsupported. Return ErrUnsupportedChallenge without echoing server challenge payloads. Missing input uses ErrInputRequired; HTTP failures expose a status via HTTPError.
  • Each login returns only its new credentials. Never merge an old refresh token into a fresh result. Token syntax checks are not JWT verification.

Read the full file on GitHub · 193 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. 12d ago Changed b1bf6fedaa86
  2. 28d ago Changed · -1 lines a83bab3e1ae0
  3. 1mo ago Changed · +2 lines · -22 tokens per session 8d2fefef32c6
  4. 1mo ago Changed · +42 lines · +9 tokens per session 817deedae63f
  5. 1mo ago First seen · 150 lines · 62 tokens per session scan A 02aafbdbfb7c

Subscribe to this mod's changes

authentication-client is a skill published in the GitHub repository greenpau/go-authcrunch (60 stars, last pushed 10d ago), licensed Apache-2.0. It adds 49 tokens to every session and 2,532 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 2026-09-13.

Related

authentication-client compared with skills from other repositories

authentication-client next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
authentication-clientgreenpau/go-authcrunchSkill6010d agoApache-2.0A49Codex
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