Agent skill

Source Code Management

by greenpau in greenpau/caddy-security

Create or review caddy-security commit messages using repository indicators, required body sections, and timestamped message files.

Apache-2.0Auto-check passedDevelopment

Install Source Code Management

skills CLI
$ npx skills add greenpau/caddy-security --skill source-code-management -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install greenpau/caddy-security source-code-management --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/greenpau/caddy-security.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.codex/skills/source-code-management .claude/skills/source-code-management && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
source-code-management
GitHub stars
2.3k
Token cost
~2.3k tokens
SKILL.md length
1,097 words
Files
2
Skills in repo
29
Repo updated
First seen
Licence
Apache-2.0

At a glance

Create or review caddy-security commit messages using repository indicators, required body sections, and timestamped message files.

  • Works in 4 steps: Before this commit → After this commit → Tests → …
  • Tasks that involve Commit messages
  • SKILL.md covers Commit Message Rules, Change Indicators, Commit Message File Workflow and Acceptance criteria
  • Calls git; reaches google.com

What it does

Source Code Management is an agent skill from greenpau/caddy-security. Create or review caddy-security commit messages using repository indicators, required body sections, and timestamped message files. A message request does not create a commit.

Its SKILL.md is about 2.3k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files (for example `agents/openai.yaml`).

It sits in Development, covering Commit messages. The repository describes itself as: 🔐 Authentication, Authorization, and Accounting (AAA) App and Plugin for Caddy v2. 💎 Implements Form-Based, Basic, Local, LDAP, OpenID Connect, OAuth 2.0 (Github, Google…. The licence is Apache-2.0.

When your agent uses it

  • Tasks that involve Commit messages

Example prompts

  • “/source-code-management”

Workflow steps

4 steps, taken from the first numbered list in SKILL.md.

  1. Before this commit
  2. After this commit
  3. Tests
  4. More info

What it can do on your machine

Read from SKILL.md and the folder at commit a48553d. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • git

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Hosts in commands or code, which the agent is likely to contact:

    • google.com

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Source Code Management loads about 2.3k tokens when it runs. Until then it costs about 50 tokens; SKILL.md has 1,097 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~50
When it runs · the whole SKILL.md, loaded when a task matches
~2.3k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from greenpau/caddy-security at commit a48553d, republished under its Apache-2.0 licence (© greenpau). 1,097 words, ~2,250 tokens.

Download SKILL.mdSave it as .claude/skills/source-code-management/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
source-code-management
description
Create or review caddy-security commit messages using repository indicators, required body sections, and timestamped message files. A message request does not create a commit.

Source Code Management

Commit Message Rules

All commits must have a proper commit message. Inspect the requested diff and git status --short, including staged and unstaged work, before describing it. Use the user's requested scope; do not include unrelated work merely because it is present in the checkout. Describe the final behavior and actual validation, not a transcript or an abandoned implementation. Creating a message does not stage files, create a commit, tag a release, or publish changes.

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 a mix of product-surface labels and maintenance labels. Prefer the most specific product surface when the change is clearly about one Caddy security directive, parser, provider, or runtime path. Use a maintenance label when the change is repository plumbing, documentation, testing, release work, or a bug fix that cuts across multiple surfaces.

Selection rules:

  • Use exactly one indicator. Do not combine indicators or add parenthesized scopes.
  • Prefer public Caddyfile and module names over internal abbreviations. For example, use authenticate instead of authn, and authorize instead of authz.
  • Use caddyfile for parser/adaptation infrastructure that affects several directives, Caddyfile fixture changes, or generic config loading.
  • Use provider indicators such as ldap, oauth, or saml only when the change is provider-specific. Use identity when the change is shared by identity stores or identity providers.
  • Use breakfix for a reported regression, panic, or shipped behavior that is visibly broken for users. Use fix for narrower correctness fixes that are not tied to a known user breakage.
  • Use tests, not unittest, for Go tests, Caddyfile adapt fixtures, and testdata changes whose primary purpose is coverage.
  • 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 or toolchain version bumps. Use build only when the build behavior itself changes.
  • The Makefile release target creates the subject ops: released v<VERSION>. For hand-written release workflow changes, use ops. Follow release-and-versioning for the release procedure and publication scope; an automated subject does not replace the body requirements for hand-written commit messages.
  • 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 authenticate for authn, authorize for authz, ldap for ids/ldap, local for ids/local, feat for feature, and tests for unittest. Replace misc or chore with a more specific indicator when possible, or ops/various when it is truly general maintenance.
  • Use colon form for new dependency bumps, such as ops: go-authcrunch to v1.1.40, even though older history has subjects like upgrade to github.com/greenpau/go-authcrunch v1.1.39.

Use one of these product-surface indicators:

  • app: Caddy security app provisioning, lifecycle, config validation, or runtime config resolution
  • authenticate: authenticate handler behavior, authentication portals, cookies, crypto, transforms, or authentication Caddyfile directives
  • authorize: authorize handler behavior, authorization policies, ACLs, bypass rules, crypto, claim extraction, or header injection
  • caddyfile: global security Caddyfile parsing, directive ordering, adapt behavior, parser helpers, or Caddyfile fixtures spanning multiple surfaces
  • credentials: credential directives and credentials config
  • identity: shared identity store or identity provider behavior
  • ldap: LDAP-specific identity store or provider behavior
  • local: local identity store or local user behavior
  • messaging: messaging directives and messaging config
  • oauth: OAuth or OpenID Connect provider behavior
  • registration: user registration directives and registration policy behavior
  • saml: SAML provider behavior
  • secrets: secrets manager directives and secret resolution behavior
  • sso: SSO provider directives and single sign-on provider config
  • ui: portal UI directives, labels, icons, metadata, themes, or UI assets
  • cmd: cmd/authcrunch wrapper behavior

Use one of these maintenance indicators:

  • breakfix: reported regression, panic, or user-visible breakage fix
  • fix: correctness fix without a known production breakage
  • feat: user-facing capability that does not fit a more specific product surface indicator
  • docs: documentation-only changes
  • tests: test additions, fixture updates, or coverage improvements
  • refactor: behavior-preserving code restructuring
  • skills: AI agent skills, skill metadata, AGENTS.md, or agent-facing repository instructions
  • ops: dependency, Caddy, Go, toolchain, release, version-reference, or repository maintenance changes
  • build: Makefile, build output, xcaddy, packaging, or local build behavior
  • github: GitHub Actions, issue templates, CLA workflow, or repository GitHub metadata
  • security: vulnerability, dependency audit, hardening, or disclosure-policy changes
  • various: intentionally mixed changes that do not fit one indicator
Show full SKILL.md (343 more words)Show less

The commit message body must contain the following sections in this order:

  1. Before this commit:
  2. After this commit:
  3. Tests:
  4. More info:

The body may also contain the following optional sections:

  1. Resolves:
  2. Partial Resolution:
  3. See also:
  4. Links:

The following rules apply to the body of a commit message:

  • Separate sections with one blank line.
  • Each section title MUST end with a colon (:).
  • Lines MUST NOT exceed 87 characters, except in Links and More info.
  • Use Resolves ONLY when the PR or commit resolves an issue completely.
  • Use Partial Resolution when the PR or commit addresses an issue partially.
  • Use See also for additional related references.
  • Resolves, Partial Resolution, and See also MUST contain valid links.
  • Multiple links in those reference sections MUST be separated by comma and space (, ).
  • Tests MUST describe the command or manual check performed.
  • If no smoke test was run, Tests MUST say not run and include the reason.
  • More info MUST summarize the implementation details or notable decisions.

The Links section must contain a list of valid links or references, e.g.:

text
  - Text reference
  - [HTTP link](http://google.com/)

Use this template for commit messages:

text
indicator: concise subject under 87 characters

Before this commit: describe the previous behavior, limitation, or state.

After this commit: describe the new behavior, implementation, or state.

Tests: describe the command or manual check performed.

More info: summarize important implementation details or decisions.

For example, a commit message may look like this:

text
docs: add contributing guidance

Before this commit: the repository had no guidance related to open-source
contributions.

After this commit: contribution guidance is documented in `CONTRIBUTING.md`.

Tests: reviewed the rendered Markdown manually.

More info: added a focused contributor workflow and repository etiquette notes.

Commit Message File Workflow

For every request to create or generate a commit message, write it below tmp/commits with a YYYYMMDD_HHMM_ prefix and always provide the corresponding git commit -F ... command. Do not require the user to ask separately for a message file. A review-only request does not create a file unless asked.

Commit message files in tmp/commits are working artifacts and should not be committed unless explicitly requested.

Acceptance criteria

  • The subject has one allowed indicator, is shorter than 87 characters, and has no final period. The required body sections appear in order and obey line limits.
  • Tests names actual commands or manual checks performed and reports omitted smoke tests with their reason. A proposed test is never described as passing.
  • A message request produces the timestamped file under tmp/commits and its git commit -F command; a review-only request does not create or commit files.

© greenpau, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file in .codex/skills/source-code-management of greenpau/caddy-security.

  • SKILL.md
  • agents/openai.yaml

Open the folder on GitHubat commit a48553d

Compare with similar skills

Source Code Management next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Source Code Management compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Source Code Management this skillgreenpau/caddy-security2.3k—~2.3kAutomated safety check: PassApache-2.0
Contextual Commit Messagesyamadashy/repomix29k1 repos~2.7kAutomated safety check: PassMIT
React Router Release Notes Prepremix-run/react-router57k—~1.1kAutomated safety check: PassMIT
Caveman Commitvishiri/fantasia-archive40913 repos~642Automated safety check: PassGPL-3.0
PR Finalize Reviewmicrosoft/garnet12k—~3.1kAutomated safety check: PassMIT
ToolJet Multi-Repo CommitToolJet/ToolJet41k—~1.3kAutomated safety check: PassAGPL-3.0

Similar skills

  • Writes Conventional Commits whose bodies carry action lines recording the intent, decisions and constraints behind a change, not only what changed.

    29k GitHub starsUsed in 1 repo~2.7k tokens
    DevelopmentAuto-check passed
  • React Router Release Notes Prep

    remix-run/react-router

    Polishes pending React Router change files before the versioning scripts run, and decides whether a long-form What's Changed section is warranted.

    57k GitHub stars~1.1k tokensUpdated today
    DevelopmentAuto-check passed
  • Caveman Commit

    vishiri/fantasia-archive

    Ultra-compressed commit message generator. An agent skill from vishiri/fantasia-archive.

    409 GitHub starsUsed in 13 repos~642 tokens
    DevelopmentAuto-check passed
  • PR Finalize Review

    microsoft/garnet

    Official

    Checks that a pull request's title and description match its implementation and reviews the code for Garnet best practices, reporting findings without posting them.

    12k GitHub stars~3.1k tokensUpdated today
    DevelopmentAuto-check passed
  • Commits changes across ToolJet's root repo and its server/ee and frontend/ee submodules, writing messages from the diffs and updating submodule pointers in order.

    41k GitHub stars~1.3k tokensUpdated today
    DevelopmentAuto-check passed
  • Git Workflow and Versioning

    addyosmani/agent-skills

    Sets git habits for every change: short-lived branches, atomic commits with descriptive messages, clean pull requests, plus versioning, tagging and changelogs for releases.

    103k GitHub starsUsed in 2 repos~3.5k tokens
    DevelopmentAuto-check: notes

More from greenpau/caddy-security

All 29 skills in this repo
  • Authentication Portal API

    greenpau/caddy-security

    Build or troubleshoot portal JSON/native login clients, refresh, profile and admin APIs, and public JWKS.

    2.3k GitHub stars~2.9k tokensUpdated 3 days ago
    Auto-check passed
  • Coding Directives

    greenpau/caddy-security

    Implement or review caddy-security Go code, Caddy modules, parsers, lifecycle, and HTTP delegation.

    2.3k GitHub stars~4.1k tokensUpdated 3 days ago
    Auto-check passed
  • Configuration

    greenpau/caddy-security

    Build or review caddy-security Caddyfiles and select focused configuration skills.

    2.3k GitHub stars~2.6k tokensUpdated 3 days ago
    Auto-check passed
  • Configuration Crypto

    greenpau/caddy-security

    Configure portal/policy JWT keys, token names and lifetimes, key loading and generation, public-key discovery, and System API encryption keys.

    2.3k GitHub stars~3.5k tokensUpdated 3 days ago
    Auto-check passed
  • Configuration HTTP Integrations

    greenpau/caddy-security

    Mount authenticate and authorize handlers, separate portal and protected routes, align auth URLs, and preserve trusted proxy metadata.

    2.3k GitHub stars~3.2k tokensUpdated 3 days ago
    Auto-check passed
  • Configuration State

    greenpau/caddy-security

    Configure durable AuthCrunch runtime state, exclusive storage ownership, stop/start persistence, reload rejection, and recovery.

    2.3k GitHub stars~1.6k tokensUpdated 3 days ago
    Auto-check passed

Categories

Questions about Source Code Management

What does Source Code Management do?

Create or review caddy-security commit messages using repository indicators, required body sections, and timestamped message files. Source Code Management is an agent skill from greenpau/caddy-security. Create or review caddy-security commit messages using repository indicators, required body sections, and timestamped message files.

When should I use Source Code Management?

Source Code Management fits situations like: tasks that involve Commit messages.

How do I install Source Code Management in Claude Code?

Run `npx skills add greenpau/caddy-security --skill source-code-management -a claude-code`. Or copy the skill folder (.codex/skills/source-code-management in greenpau/caddy-security) into .claude/skills/source-code-management in your project. Claude Code loads it when a task matches its description.

How do I install Source Code Management in Codex?

Run `npx skills add greenpau/caddy-security --skill source-code-management -a codex`. Or copy the skill folder (.codex/skills/source-code-management in greenpau/caddy-security) into .agents/skills/source-code-management in your project. Codex loads it when a task matches its description.

Can I use Source Code Management in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add greenpau/caddy-security --skill source-code-management -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/source-code-management, .gemini/skills/source-code-management, .github/skills/source-code-management and .opencode/skills/source-code-management in your project.

What does Source Code Management need to run?

Going by SKILL.md and its folder, Source Code Management needs the command-line tools its instructions call (git).

Does Source Code Management access the network?

SKILL.md names 1 domain. In commands or code: google.com; the agent is likely to contact it when it follows the instructions. This is read from the text; nothing was executed.

Is Source Code Management safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Source Code Management use?

Source Code Management is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Source Code Management use?

About 2.3k tokens (SKILL.md is roughly 9k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Source Code Management?

Skills that share tags, products or a category with Source Code Management: Contextual Commit Messages (yamadashy/repomix, 29k stars), React Router Release Notes Prep (remix-run/react-router, 57k stars), Caveman Commit (vishiri/fantasia-archive, 409 stars) and PR Finalize Review (microsoft/garnet, 12k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Source Code Management?

greenpau (a GitHub user) maintains it in greenpau/caddy-security, which has 2,252 GitHub stars. The repository holds 29 skills in this directory. The repository was last updated on October 5, 2026.

Source: greenpau/caddy-security on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.