Skip to main content
command CX Codex

speckit.companion.mark-complete — Claude Code command: mark spec done

speckit.companion.mark-complete marks the active spec as completed via write-context.py. Handy when you want to close a spec by hand instead of running a full converge.

MIT ★ 110 updated 2026-11-03

Install into Claude Code · Manually: put the files in place All methods and platforms ↓
.claude/commands/speckit.companion.mark-complete.md
Open on GitHub

What speckit.companion.mark-complete does

The command runs python3 .specify/extensions/companion/scripts/write-context.py --mark-complete --by ai from the repository root. That writes the completed status into the active spec's context. A clean converge already does this after implementation, so the command exists for manual marking.

It needs python3 on PATH. If the interpreter is absent, the command reports that the spec was not marked and keeps going. Nothing breaks, but the status stays unchanged.

Installation is a file placement. For Claude Code, put it at .claude/commands/speckit.companion.mark-complete.md. Codex uses ~/.codex/prompts/speckit.companion.mark-complete.md.

What it helps with

  • mark a spec completed without another converge
  • write the completed status to the active spec context
  • close a spec right after implementation
  • sync state after manual edits

Example prompts for the agent

  • /speckit.companion.mark-complete
  • Mark the spec completed with /speckit.companion.mark-complete

How to install speckit.companion.mark-complete

Manually: put the files in place

.claude/commands/speckit.companion.mark-complete.md

Call it with /speckit.companion.mark-complete. For all projects use ~/.claude/commands/

Questions about speckit.companion.mark-complete

How do I install speckit.companion.mark-complete in Claude Code?

Place the command file at .claude/commands/speckit.companion.mark-complete.md inside your project repository. It then becomes available as /speckit.companion.mark-complete.

What does this command do?

It runs write-context.py with the --mark-complete flag to write the completed status into the active spec's context. A clean converge normally does this itself, so the command covers manual marking.

What happens if python3 is missing?

The command says the spec was not marked and carries on. The status stays unchanged, so you'll want python3 installed beforehand.

Source text

speckit.companion.mark-complete.md · MIT
---
description: "Mark the active spec completed by hand (writes status: completed)"
---

# Mark Spec Complete

Run this from the repository root to mark a spec that finished implement as completed (a clean converge already does it on its own); if `python3` is missing, say the spec was not marked and carry on.

```bash
python3 .specify/extensions/companion/scripts/write-context.py --mark-complete --by ai
```

© alfredoperez · MIT · alfredoperez/speckit-companion

Similar slash commands

All slash commands for Agent setup: memory, context, orchestration →

From the same set83

The whole set →
speckit.git.feature The speckit.git.feature command creates and checks out a Git feature branch from a specification. Configure sequential or timestamp numbering and shape branch names with a template. CX Codex +1 ★ 110repo stars speckit-git-feature speckit-git-feature is a Claude Code skill that creates a Git branch from a task description within a Spec Kit project and reads its configuration. CX Codex +1 ★ 110repo stars speckit.companion.living-move speckit.companion.living-move relocates Speckit living specs between central storage and colocated code folders while updating the project registry. CX Codex +1 ★ 110repo stars publish-mod publish-mod releases the Claude Code mod through the repository marketplace and prepares the Anthropic directory handoff for the user. CX Codex +1 ★ 110repo stars speckit.constitution speckit.constitution updates the project constitution template in .specify/memory/constitution.md and aligns dependent specification templates. CX Codex GP ChatGPT ★ 110repo stars bench-run-all The bench-run-all command runs one benchmark size across three cells, drives the agent steps, then judges and captures the results. It is built for Speckit pipeline comparisons. CX Codex +1 ★ 110repo stars publish-canvas publish-canvas ships the Copilot app canvas: version bump, tests, the canvas-v<X.Y.Z> tag, then the github/awesome-copilot listing update. CX Codex +1 ★ 110repo stars bench-replay The bench-replay command for Claude Code and Codex replays one pipeline step from a saved stage and grades the effect of a change. CX Codex +1 ★ 110repo stars

Project sponsors

Companies that keep this analytics open