construct

A software-building workflow that combines iterative construction with test-driven development, or TDD, where tests are written before the code they check.

In plain words
What is it for?
It helps implement tasks in small slices, write a failing test, add the minimum code needed, refactor safely, commit the result, and check for regressions.
Why use it?
It catches mistakes early and keeps each change tied to a clearly defined expected behavior.

Command for Claude Code

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/varunk130/ai-workflow-playbooks/construct
Clone the repo
git clone --depth 1 https://github.com/varunk130/ai-workflow-playbooks

Made for: Claude Code.

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 130 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 $0.00000 $0.00130
Opus 5 $0.00000 $0.00065
Sonnet 5 $0.00000 $0.00026
Haiku 4.5 $0.00000 $0.00013

Measured 2d ago against content hash e8ee7b86799f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

construct 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.

.claude/commands/construct.md · 14 lines

What it actually says

Run the CONSTRUCT stage of the AI Workflow Playbooks pipeline.

Load and execute these playbooks together:

  1. playbooks/iterative-construction/PLAYBOOK.md - Build in thin vertical slices with continuous verification
  2. playbooks/test-first-engineering/PLAYBOOK.md - Write tests before implementation code

For each task in the implementation sequence:

  • Write a failing test that captures the expected behavior
  • Implement the minimum code to make the test pass
  • Refactor for clarity while keeping tests green
  • Commit after each completed task

Verify all tests pass and no regressions are introduced before marking a task complete.

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 · 14 lines · 0 tokens per session scan A e8ee7b86799f

Subscribe to this mod's changes

construct is a command published in the GitHub repository varunk130/ai-workflow-playbooks (2 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 130 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 2026-08-31.