lifecycle

lifecycle is a command for Claude Code from github/spec-kit-copilot. It costs 0 tokens per session (1,519 once invoked), scanned A, original, MIT.

A lifecycle hook layer for Specify extension commands, which add checkpoints around planning and implementation workflows. It runs checks before and after commands such as specifying requirements, planning, creating tasks, and implementing them.

In plain words
What is it for?
Use it to add controlled lifecycle checkpoints around supported Specify commands while preserving their approval gates, prerequisites, and validation steps.
Why use it?
It ensures the extension's pre- and post-run checks happen once and use the same command context. It also prevents these hooks from being confused with Copilot's built-in events or from changing the selected workflow's safeguards.

Command for Claude Code ✓ vendor

Written for Claude Code: a Claude Code command (commands/*.md).

Good fit Use it to add controlled lifecycle checkpoints around supported Specify commands while preserving their approval gates, prerequisites, and validation steps.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/github/spec-kit-copilot/lifecycle
About the project

github/spec-kit-copilot is a repository of GitHub Copilot integrations for Spec Kit, a toolkit for developing software through a structured specification-first workflow. It provides Copilot-specific commands, skills, canvases, and related workflow components for users of the Copilot CLI, Copilot App, and VS Code.

github/spec-kit-copilot · 22 stars · on 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.

Clone the repo
git clone --depth 1 https://github.com/github/spec-kit-copilot

Made for: Claude Code.

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 lifecycle

README.md
[![agentmods](https://agentmods.dev/badge/commands/github/spec-kit-copilot/lifecycle/github.svg)](https://agentmods.dev/commands/github/spec-kit-copilot/lifecycle)
Your own site
<a href="https://agentmods.dev/commands/github/spec-kit-copilot/lifecycle"><img src="https://agentmods.dev/badge/commands/github/spec-kit-copilot/lifecycle/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 lifecycle

Your own site · 80×15
<a href="https://agentmods.dev/commands/github/spec-kit-copilot/lifecycle"><img src="https://agentmods.dev/badge/commands/github/spec-kit-copilot/lifecycle.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,519 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 $0.00000 $0.01519
Opus 5.5 $0.00000 $0.00608
Sonnet 5.5 $0.00000 $0.00304
Haiku 4.5 $0.00000 $0.00152

Measured today against content hash c22f74258c8b, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

lifecycle 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 today.

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.

spec-kit-presets/copilot-extension-hooks/commands/lifecycle.md · 135 lines

How it starts

The opening of the file, as written. The whole thing — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Copilot extension lifecycle checkpoints

This layer handles Specify extension lifecycle hooks, not Copilot native hooks/events. It adds no baseline artifacts, phases, or prerequisite exemptions. Read the selected baseline below, consider its User Input, and respect its scope and safeguards before dispatching anything.

Capture the current loaded skill's name, speckit-<command>, once for this invocation. <command> must be one of constitution, specify, clarify, plan, tasks, analyze, checklist, implement, or converge. Use that captured command for both events, even while invoking a hook's skill. Do not dispatch hooks for another command or for taskstoissues.

Apply these checkpoints exactly once per invocation:

  1. Run Pre-Execution Checks below before starting the baseline workflow, whether it begins with Outline, Goal, or Execution Steps.
  2. Execute the selected baseline unchanged, including all its artifact prerequisites, user approval gates, read-only boundaries, and validation.
  3. Run Post-Execution Checks below at the established completion checkpoint:
    • For specify, clarify, plan, tasks, and implement, after successful workflow/validation and before the baseline Completion Report (or its equivalent final summary). Defer that report until post-hooks finish; do not stop at an earlier Done When list or report instruction.
    • For constitution and checklist, after the baseline update/generation and its summary.
    • For analyze, after the analysis report and remediation offer.
    • For converge, after producing and reporting converged or tasks_appended in-session, before listing hooks. A completed Lean assessment that reports remaining work already covered by existing open tasks also reaches this checkpoint, even when nothing is appended. This is not convergence and must not be reported as such. Blocked or unverified assessments do not reach it.

Do not run successful-completion post-hooks if the baseline stops on a failed prerequisite, gate, or validation. Never use a hook to bypass such a stop. This is the sole lifecycle dispatcher in the supported baseline composition: do not perform a second hook pass for a baseline report, Done When item, or EXECUTE_COMMAND marker. Track each dispatched (event, extension, command) in this invocation; do not invoke it twice, automatically retry it, or re-enter the current lifecycle command recursively. This tracking is session guidance, not a persistent lock or host-enforced guarantee.

Read the full file on GitHub · 135 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. today First seen · 135 lines · 0 tokens per session scan A c22f74258c8b

Subscribe to this mod's changes

lifecycle is a command published in the GitHub repository github/spec-kit-copilot (22 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,519 tokens. 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 2026-10-29.