A sample command that shows how to build a command for a Spec Kit extension. It is a template with placeholder steps, settings, and prerequisites.

Use it as a starting point when creating or documenting a Spec Kit extension command. The example is incomplete, so it does not describe a finished task.

It gives extension authors a concrete structure to copy when learning how commands can load settings, check requirements, and perform an action.

example — Command by github

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods

npx agentmods add commands/github/spec-kit/example

Clone the repo

git clone --depth 1 https://github.com/github/spec-kit

Per session 6 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,042 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

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.

Model	Per session	Once invoked
Fable 5	$0.00006	$0.01042
Opus 5	$0.00003	$0.00521
Sonnet 5	$0.00001	$0.00208
Haiku 4.5	$0.00001	$0.00104

Measured yesterday against content hash 4d23361bc7b3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

example 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

example — 95% identical, 3 lines differ

extensions/template/commands/example.md · 211 lines

How it starts

The opening of the file, as written. The whole thing — 211 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Example Command

This is an example command that demonstrates how to create commands for Spec Kit extensions.

Purpose

Describe what this command does and when to use it.

Prerequisites

List requirements before using this command:

Prerequisite 1 (e.g., "MCP server configured")
Prerequisite 2 (e.g., "Configuration file exists")
Prerequisite 3 (e.g., "Valid API credentials")

User Input

$ARGUMENTS

Steps

Step 1: Load Configuration

Load extension configuration from the project:

``bash config_file=".specify/extensions/my-extension/my-extension-config.yml"

if [ ! -f "$config_file" ]; then echo "❌ Error: Configuration not found at $config_file" echo "Run 'specify extension add my-extension' to install and configure" exit 1 fi

Read configuration values

setting_value=$(yq eval '.settings.key' "$config_file")

Apply environment variable overrides

setting_value="${SPECKIT_MY_EXTENSION_KEY:-$setting_value}"

Validate configuration

if [ -z "$setting_value" ]; then echo "❌ Error: Configuration value not set" echo "Edit $config_file and set 'settings.key'" exit 1 fi

echo "📋 Configuration loaded: $setting_value" ``

Step 2: Perform Main Action

Describe what this step does:

``markdown Use MCP tools to perform the main action:

Tool: example-mcp-server example_tool
Parameters: { "key": "$setting_value" }

This calls the MCP server tool to execute the operation. ``

Step 3: Process Results

Process the results and provide output:

bash echo "" echo "✅ Command completed successfully!" echo "" echo "Results:" echo " • Item 1: Value" echo " • Item 2: Value" echo ""

Step 4: Save Output (Optional)

Save results to a file if needed:

``bash output_file=".specify/my-extension-output.json"

Read the full file on GitHub · 211 lines

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.

yesterday First seen · 211 lines · 6 tokens per session scan A 4d23361bc7b3

Subscribe to this mod's changes

example is a command published in the GitHub repository github/spec-kit (132,298 stars, last pushed 3d ago), licensed MIT. It adds 6 tokens to every session and 1,042 once invoked, about $0.0000 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 2026-08-30.

Planning ai copilot development engineering prd spec

example