speckit-init

A setup command that creates a Spec Kit project for GitHub Copilot, a coding assistant, using Copilot's skills format.

In plain words
What is it for?
Use it when starting Spec Kit in a new project or adding it to an existing one.
Why use it?
It adds the templates, scripts, and commands needed to use specification-led development in a repository.

Skill for Claude CodeCodex

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 skills/github/spec-kit-copilot/speckit-init
Any agent
npx skills add github/spec-kit-copilot --skill speckit-init
Clone the repo
git clone --depth 1 https://github.com/github/spec-kit-copilot

Made for: Claude Code, Codex.

Per session 113 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,305 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.

ModelPer sessionOnce invoked
Fable 5 $0.00113 $0.01305
Opus 5 $0.00056 $0.00652
Sonnet 5 $0.00023 $0.00261
Haiku 4.5 $0.00011 $0.00130

Measured 2d ago against content hash 78210fd22063, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

speckit-init 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 2d 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.

skills/speckit-init/SKILL.md · 106 lines

How it starts

The opening of the file, as written. The whole thing — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Spec Kit — init

Initialize a spec-driven development project for GitHub Copilot with the Specify CLI (specify). This skill exposes the specify init command. You (the agent) run the CLI on the user's behalf via the shell; the CLI does the scaffolding.

Because this is the Copilot plugin, always scaffold Copilot in skills mode:

--integration copilot --integration-options="--skills"

This installs spec-kit commands (and any extensions added later) as Copilot Agent Skills.github/skills/speckit-<cmd>/SKILL.md — rather than the default .github/agents/*.agent.md layout. Skills are what Copilot CLI discovers as SKILL.md, so this keeps the project consistent with how this plugin works. Do not omit --integration-options="--skills".

Prerequisite

This skill needs the specify CLI. Confirm it is available:

specify --version

If it is missing (command not found), use the speckit-cli-setup skill to install it first, then continue.

When to use

  • The user wants to start a new spec-kit project.
  • The user wants to add spec-driven development to the current directory.

How to invoke

specify init scaffolds templates, scripts, the spec-kit workflow, shared infrastructure, and the Copilot command files. It runs offline from assets bundled in the installed CLI.

Common forms (always Copilot + skills mode). Pick the --script flavor for the user's OS — sh on macOS/Linux, ps on Windows (the examples below use sh; swap in --script ps on Windows):

# New project directory
specify init <project-name> --integration copilot --integration-options="--skills" --script sh

# Initialize in the current directory
specify init . --integration copilot --integration-options="--skills" --script sh
specify init --here --integration copilot --integration-options="--skills" --script sh

# Current directory is non-empty: skip the confirmation prompt
specify init --here --integration copilot --integration-options="--skills" --script sh --force

# Install a preset at init time
specify init <project-name> --integration copilot --integration-options="--skills" --script sh --preset healthcare-compliance

Read the full file on GitHub · 106 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.

  1. 2d ago First seen · 106 lines · 113 tokens per session scan A 78210fd22063

Subscribe to this mod's changes

speckit-init is a skill published in the GitHub repository github/spec-kit-copilot (11 stars, last pushed 6d ago), licensed MIT. It adds 113 tokens to every session and 1,305 once invoked, about $0.0006 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.