A command that implements a feature from its written task breakdown, using test-first development, delegated work, parallel tasks, and review checkpoints.

Use it to execute a feature specification phase by phase and update its task and progress files.

It provides a structured way to move from planned tasks to completed code while checking progress along the way.

How HelixDevelopment/code configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to HelixDevelopment/code. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/HelixDevelopment/code/main/.specify/extensions/superspec/commands/execute.md

Clone the repo

git clone --depth 1 https://github.com/HelixDevelopment/code

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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/helixdevelopment/code/execute/github.svg)](https://agentmods.dev/commands/helixdevelopment/code/execute)

Your own site

<a href="https://agentmods.dev/commands/helixdevelopment/code/execute"><img src="https://agentmods.dev/badge/commands/helixdevelopment/code/execute/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.

Your own site · 80×15

<a href="https://agentmods.dev/commands/helixdevelopment/code/execute"><img src="https://agentmods.dev/badge/commands/helixdevelopment/code/execute.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 474 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.

Model	Per session	Once invoked
Fable 5.1	$0.00000	$0.00474
Opus 5	$0.00000	$0.00237
Sonnet 5	$0.00000	$0.00095
Haiku 4.5	$0.00000	$0.00047

Measured 4d ago against content hash 5f1530527c3d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

execute 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 4d 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.

.specify/extensions/superspec/commands/execute.md · 60 lines

What it actually says

speckit.superspec.execute

Orchestrate implementation with TDD, subagents, and review gates.

Usage

/speckit.superspec.execute [spec-number|spec-path]

Process

Read the tasks file for the target feature
Read the plan and constitution for context
Superpowers detection: Check for executing-plans, subagent-driven-development, and test-driven-development skills
Walk through tasks phase by phase:

For [TDD] tasks:
- If TDD skill found, follow its RED-GREEN-REFACTOR process
- Otherwise: write test → verify it fails → implement → verify it passes → refactor
For [SUBAGENT] tasks:
- If subagent-driven-development skill found, follow its dispatch protocol
- Otherwise: implement sequentially in-session
For [P] tasks:
- Launch parallel tasks where possible using the Task tool
For [REVIEW] tasks:
- Pause and run review protocol (see commands/review.md)
At each phase checkpoint:
- Summarize completed work
- Run tests if applicable
- Ask user for approval before proceeding to next phase
Update task checkboxes in tasks.md as each task completes
Update specs/NNN/progress.yml with current execution state

Output

Code changes in the project, updated task checkboxes in tasks.md.

Human Checkpoints

The agent MUST pause at every phase boundary and wait for explicit user approval. Never skip a checkpoint.

Superpowers Adaptation

Skill	Adaptation
`executing-plans`	Follow its batch processing protocol with human checkpoints
`subagent-driven-development`	Follow its dispatch protocol for `[SUBAGENT]` tasks
`test-driven-development`	Follow its RED-GREEN-REFACTOR discipline for `[TDD]` tasks

If no superpowers are available, all three fall back to built-in sequential execution with manual confirmation. See references/superpowers-bridge.md for full details.

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.

4d ago First seen · 60 lines · 0 tokens per session scan A 5f1530527c3d

Subscribe to this mod's changes

execute is a command published in the GitHub repository HelixDevelopment/code (2 stars, last pushed 3d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 474 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 2026-09-04.

Planning Project management agent agentic-ai agents ai ai-agents cli

trellis-continue

Resume work on the current task — pick up at the right phase/step in .trellis/workflow.md.

tincopper/neeko · 0 tokens

trellis-finish-work

Wrap up the current session: archive the active task (and any other completed-but-unarchived tasks the user wants to clean up) and record the session journal. Code commits are NOT done here — those happen in workflow Phase 3.4 before you invoke this command.