Write Navin slash commands as Markdown prompt files (frontmatter, $ARGUMENTS, $1..$9, ${1:-default}, @file inlining, !`cmd` shell output, allowed-tools, namespaces, plugin commands with ${NAVIN_PLUGIN_ROOT}). Use when the user asks to "create a slash command", "add a custom command", "write a command that takes arguments", "inline a file in a command", "run a shell command inside a command", "restrict the tools of a command", "add a command to my plugin", or asks how Markdown commands are…
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# Command Development
A slash command is a Markdown file whose body is a prompt. When the user types
`/<name> <arguments>`, Navin expands the file (arguments, referenced files,
shell output) and runs the result as one agent turn. Commands package a
repeatable workflow behind a short name: a review checklist, a release routine,
a scaffold.
## Commands are instructions for Navin
The body is written **for Navin**, not for the user. It gives instructions
("Review the staged diff and report..."), never a message ("This command will
review your code"). The user sees the result of the turn, not the prompt.
Correct:
```markdown
Review the staged changes for security issues: injection, unsafe file access,
secrets in code. Report each finding with file, line and severity.
```
Wrong:
```markdown
This command reviews your code for security issues and you will get a report.
```
## Where commands live
| Scope | Folder | Notes |
|---|---|---|
| Project | `<workspace>/.navin/commands/` | shared with the repository |
| Personal | `~/.navin/commands/` | every workspace of this user |
| Plugin | `<plugin>/commands/` (or the `commands` paths of `plugin.json`) | while the plugin is enabled |
…
The line at the top of this page pins the label git:20261024.772383e, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
GET https://markdownregistry.com/api/v1/artifacts/art_bvwragyfyxpshfhr
GET https://markdownregistry.com/api/v1/resolve?ref=navinspire-ia/navin/command-development
GET https://markdownregistry.com/api/v1/blob/ad337c55fd23edc5c251eaf365ae9210dc42b5d988e155a8768b17601de1064f
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
navinspire-ia/navin · navin/skills/account-research/SKILL.md · Build a complete account sheet before a meeting - company, people, news, tech, pains, and talking angles. Use before…
navinspire-ia/navin · navin/skills/adaptive-reasoning/SKILL.md · Choose the right depth of reasoning for the task - shallow for routine edits, deep for architecture, security, or…
navinspire-ia/navin · navin/skills/agent-creator/SKILL.md · Create custom subagents for Navin (agent definition files under .navin/agents or ~/.navin/agents) that the model…
navinspire-ia/navin · navin/skills/agent-development/SKILL.md · Design and write Navin subagents (agents/<name>.md with name, description and examples, tools, model, color, and a…
navinspire-ia/navin · navin/skills/algorithmic-art/SKILL.md · Generates original algorithmic art with p5.js - seeded randomness, flow fields, particle systems, noise and parametric…
navinspire-ia/navin · navin/skills/app-capacitor-builder/SKILL.md · App Factory mobile builder. Wrap the web frontend with Capacitor 8 inside os/<target> and build Android (.apk, .aab)…
anthropics/claude-plugins-official · plugins/plugin-dev/skills/command-development/SKILL.md · This skill should be used when the user asks to "create a slash command", "add a command", "write a custom command"…
nota-america/forgecat-agent-profiles · profiles/anthropics/claude-plugins-official/anthropics_claude-plugins-official_plugin-dev/for-claude/.claude/skills/command-development/SKILL.md · This skill should be used when the user asks to "create a slash
nota-america/forgecat-agent-profiles · profiles/anthropics/claude-plugins-official/anthropics_claude-plugins-official_plugin-dev/for-forgecat/skills/command-development/SKILL.md · This skill should be used when the user asks to "create a slash command", "add a command", "write a custom command"…
nota-america/forgecat-agent-profiles · profiles/anthropics/claude-plugins-official/anthropics_claude-plugins-official_plugin-dev/for-forgecat/platforms/cursor/.cursor/skills/command-development/SKILL.md · This skill should be used when the user asks to "create a slash command", "add a command", "write a custom command"…
nota-america/forgecat-agent-profiles · profiles/anthropics/claude-plugins-official/anthropics_claude-plugins-official_plugin-dev/for-cursor/.cursor/skills/command-development/SKILL.md · This skill should be used when the user asks to "create a slash
nota-america/forgecat-agent-profiles · profiles/anthropics/claude-plugins-official/anthropics_claude-plugins-official_plugin-dev/for-forgecat/platforms/codex/.agents/skills/command-development/SKILL.md · This skill should be used when the user asks to "create a slash command", "add a command", "write a custom command"…
nota-america/forgecat-agent-profiles · profiles/anthropics/claude-plugins-official/anthropics_claude-plugins-official_plugin-dev/for-codex/.agents/skills/command-development/SKILL.md · This skill should be used when the user asks to "create a slash command", "add a command", "write a custom command"…
sivan757/dsh-agent-plugins-market · plugins/plugin-dev/skills/command-development/SKILL.md · This skill should be used when the user asks to "create a slash command", "add a command", "write a custom command"…