go-authcrunch: Skill for Codex

.codex/skills/authdb/SKILL.md

authdb is a skill for Codex from greenpau/go-authcrunch. It costs 43 tokens per session (2,429 once invoked), scanned A, original, Apache-2.0.

Instructions for maintaining AuthDB, a standalone Go web server that handles authentication-related data and exposes HTTP endpoints. They cover its command, HTTP settings, configuration parsing, TLS, shutdown, tests, and deployment guidance.

In plain words
What is it for?
Use them when changing the AuthDB server, its HTTP listener or routes, configuration parser, TLS setup, signal handling, executable tests, or deployment documentation.
Why use it?
They keep the command-line server, reusable HTTP layer, configuration format, and operating instructions consistent while avoiding unsafe startup or shutdown behavior.

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='./cmd/authdb ./pkg/httpserver/...' COVERAGE_DIR=.coverage/authdb.

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/authdb/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 authdb

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/greenpau/go-authcrunch/authdb"><img src="https://agentmods.dev/badge/skills/greenpau/go-authcrunch/authdb.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 43 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,429 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 $0.00043 $0.02429
Opus 5.5 $0.00017 $0.00972
Sonnet 5.5 $0.00009 $0.00486
Haiku 4.5 $0.00004 $0.00243

Measured 12d ago against content hash 70bbb441705b, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

authdb 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/authdb/SKILL.md · 192 lines

How it starts

The opening of the file, as written. The whole thing — 192 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AuthDB Server

cmd/authdb runs AuthCrunch with Go's net/http, without Caddy. The user-facing cmd/authdb/README.md owns usage instructions, the JSON envelope, bootstrap, listener settings, and operating guidance. Keep its examples synchronized with the executable and the credential-free cmd/authdb/config.json. Use configuration integration for the reusable Go host boundary.

Ownership

  • cmd/authdb/main.go owns command flags, strict bounded JSON file loading, version metadata, production logging, TCP binding, and SIGINT/SIGTERM handling.
  • pkg/httpserver.Config and PortalRoute own transport defaults and semantic validation. The CLI's http object is this public config; security is the existing root authcrunch.Config, not a new copy of its feature models.
  • pkg/httpserver/parser.NewHTTPServerConfigFromDirectives([]string) returns (*httpserver.Config, error). It parses encoded block-body statements and calls Config.Validate; no file access, listeners, or provisioning occur.
  • pkg/httpserver.Serve(ctx, listener, config, security, logger) takes ownership of the listener immediately, including on error, and owns its constructed root runtime until all admitted requests have finished. Pass a fresh security graph and do not mutate it while serving.

The host checks serialized object collections before provisioning: optional objects can be absent, but typed collections cannot contain null objects. Use explicit typed traversal and generic pointer-collection checks, without runtime reflection. TestSecurityConfigurationObjectCoverage discovers the declared JSON model in test code and checks concrete/null objects at every collection path. Extend the typed traversal whenever that model adds a new object collection, including external refresh stores, access signers, registries, identity stores/providers and policy access_list_fields. Reject null external entries before runtime provisioning and release the owned listener on failure; TestE2EHTTPServerRejectsNullExternalConfiguration checks the public host API. Keep provider params values owned by their validators. Errors identify field paths and indices, never map keys or configured values. Guard incomplete raw crypto statements before calling the legacy KMS decoder. Initialization errors expose a redacted message; their wrapped causes are available to embedding code for private diagnostics and may contain credentials. Do not print those causes from the executable.

Read the full file on GitHub · 192 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 · +14 lines 70bbb441705b
  2. 26d ago Changed · +8 lines c92eaa6a5c11
  3. 1mo ago Changed · +5 lines 5d28f0339516
  4. 1mo ago Changed · +1 lines 1d6a400eb585
  5. 1mo ago Changed · +8 lines 756833e6ff49
  6. 1mo ago First seen · 156 lines · 43 tokens per session scan A f9b19ac58b90

Subscribe to this mod's changes

authdb is a skill published in the GitHub repository greenpau/go-authcrunch (60 stars, last pushed 10d ago), licensed Apache-2.0. It adds 43 tokens to every session and 2,429 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 2026-09-18.

Related

authdb compared with skills from other repositories

authdb next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
authdbgreenpau/go-authcrunchSkill6010d agoApache-2.0A43Codex
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