go-authcrunch: Skill for Codex

.codex/skills/source-code-management/SKILL.md

source-code-management is a skill for Codex from greenpau/go-authcrunch. It costs 44 tokens per session (2,748 once invoked), scanned A, original, Apache-2.0.

A Git workflow guide for inspecting repository status and separating staged changes from unstaged changes. It also defines rules for writing commit messages.

In plain words
What is it for?
Use it when reviewing changes, preparing commit messages, or deciding which files and diffs belong in a commit.
Why use it?
It prevents accidental index changes and makes it clear which changes a proposed commit describes. It provides a consistent format for commit subjects.

Skill for Codex

Written for Codex: agents/openai.yaml present. Also seen: mentions AGENTS.md.

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 →

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/source-code-management/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 source-code-management

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/greenpau/go-authcrunch/source-code-management"><img src="https://agentmods.dev/badge/skills/greenpau/go-authcrunch/source-code-management.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 44 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,748 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 $0.00044 $0.02748
Opus 5 $0.00022 $0.01374
Sonnet 5 $0.00009 $0.00550
Haiku 4.5 $0.00004 $0.00275

Measured yesterday against content hash 18b5afd1f68d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-14, from the pricing page.

Security

Grade A, and why

source-code-management 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.

.codex/skills/source-code-management/SKILL.md · 255 lines

How it starts

The opening of the file, as written. The whole thing — 255 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Source Code Management

Change Inspection

Inspect status, staged diff, and unstaged diff separately. Never change the index unless asked. Default a commit-message request to staged changes when the index is nonempty and state which unstaged changes are excluded. If the index is empty, describe the working-tree changes and say they must be staged before committing.

Commit Message Rules

All commits must have a proper commit message.

A hand-written commit message subject line must conform to the following rules:

  • The first line of each commit message is the subject.
  • The subject line MUST be less than 87 characters long.
  • The subject line MUST NOT terminate with a period (.).
  • The subject line MUST start with a change indicator followed by a colon (:).

Change Indicators

This repository uses change indicators as package and subsystem labels, plus a small set of maintenance labels. Prefer the most specific AuthCrunch package, CLI, provider, store, or runtime surface when the change is clearly anchored in one component. Use a maintenance label when the change is repository plumbing, documentation, tests, release work, or a deliberately cross-cutting fix.

Selection rules:

  • Use exactly one indicator. Do not combine indicators or add parenthesized scopes.
  • Prefer names that match repository packages, CLI names, or externally visible AuthCrunch concepts. For example, use authn, authz, oauth, ldap, kms, or authdbctl when a change is anchored there.
  • Use config only for top-level authcrunch.Config, Server wiring, cross-surface validation, reload plumbing, or shared config exposure. For package-local config parsing, use the package indicator.
  • Use authn for authentication portal behavior and portal API or HTTP handlers. Use ui for embedded portal/profile UI assets, templates, static assets, icons, profile UI bundles, and UI-specific serving behavior. Use cookie for cookie-specific issuing, reading, deletion, domain, and name config, even when the code lives under pkg/authn/cookie.
  • Use authz for authorization gatekeepers and policies. Use acl when the change is really the shared ACL engine, and authproxy when it is remote/basic/API-key auth proxy configuration or authenticators.
  • Use idp and ids for shared identity provider or identity store config, interfaces, and dispatch. Use oauth, saml, ldap, or local when the change is specific to that provider or store implementation.
  • Use identity for identity and user data models, local user database records, roles, passwords, MFA tokens, API keys, WebAuthn/U2F/GPG/SSH keys, lockouts, QR codes, and pkg/user.
  • Use registry for user registration providers, local registry behavior, and domain restriction rules.
  • Use kms for crypto keys, keystores, token encryption/decryption, and crypto config parsing. Use system for system API protocol messages, request parsing, generated keys, and system API auth messages.
  • Use redirects, authchal, credentials, messaging, translate, waf, apiauth, errors, requests, shared, tagging, or util when the primary change is in that package or its testdata.
  • Use authdbctl for the CLI under cmd/authdbctl, including its README, config, commands, output, and command behavior. Use build only when build output or Makefile build behavior changes.
  • Use breakfix for a reported break-fix issue, regression, panic, or shipped behavior that is visibly broken for users. Use fix for narrower correctness fixes that are not tied to known user breakage.
  • Use security for vulnerability fixes, hardening, dependency-audit work, or disclosure-policy changes. If a security fix is tightly scoped to one runtime surface, prefer the surface only when the issue is being handled as ordinary correctness rather than as a vulnerability.
  • Use tests, not unittest, for Go tests, fixtures, golden data, testdata, and coverage-only changes. If tests accompany a product change, choose the product indicator instead.
  • Use skills for AI agent skills, skill metadata, or agent-facing repository instructions. Prefer it over docs or ops when the primary purpose is helping AI agents work with this repository.
  • Use ops for dependency, Go toolchain, generated license/version metadata, release, or repository maintenance changes. Use github for GitHub Actions, issue templates, CLA workflow/assets, Funding metadata, or other GitHub repository metadata.
  • Automated patch and minor releases use ops: released v<VERSION>. Use release-and-versioning for the release workflow. Hand-written release workflow changes also use ops.
  • Use various only when a commit intentionally spans unrelated surfaces and no more specific indicator is honest.
  • Normalize older repository labels when creating new messages: use feat for feature, fix or breakfix for bug/bugfix, authdbctl for cmd changes to the CLI, github for cla bot/workflow metadata, and a specific package indicator instead of auth, api, hosting, misc, or chore.
  • Use colon form for new dependency bumps, such as ops: upgrade golang.org/x/crypto to v0.48.0, even though older history has subjects without a change indicator.

Read the full file on GitHub · 255 lines

Files

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.

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 · 255 lines · 44 tokens per session scan A 18b5afd1f68d

Subscribe to this mod's changes

source-code-management is a skill published in the GitHub repository greenpau/go-authcrunch (59 stars, last pushed yesterday), licensed Apache-2.0. It adds 44 tokens to every session and 2,748 once invoked, about $0.0002 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 2026-09-13.