build

build is a command for Claude Code from luanmorenommaciel/agentspec. It costs 16 tokens per session (1,223 once invoked), scanned A, original, MIT.

Execute implementation with on-the-fly task generation (Phase 3).

Command for Claude Code

Installs and runs on its own, but its text points at files inside the plugin that ships it — anything it tells you to read at a ${CLAUDE_PLUGIN_ROOT} path is only there once the plugin is installed.

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/luanmorenommaciel/agentspec/build
Clone the repo
git clone --depth 1 https://github.com/luanmorenommaciel/agentspec

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 build

README.md
[![agentmods](https://agentmods.dev/badge/commands/luanmorenommaciel/agentspec/build.svg)](https://agentmods.dev/commands/luanmorenommaciel/agentspec/build)
Your own site
<a href="https://agentmods.dev/commands/luanmorenommaciel/agentspec/build"><img src="https://agentmods.dev/badge/commands/luanmorenommaciel/agentspec/build.svg" alt="Measured on agentmods" height="20"></a>
Per session 16 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,223 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 $0.00016 $0.01223
Opus 5 $0.00008 $0.00611
Sonnet 5 $0.00003 $0.00245
Haiku 4.5 $0.00002 $0.00122

Measured 2d ago against content hash 47534cd978a2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

build 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/workflow/build.md · 138 lines

How it starts

The opening of the file, as written. The whole thing — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Build Command

Execute implementation with on-the-fly task generation (Phase 3)

Usage

/build <design-file> [--judge[=MODE]]

Examples

/build .claude/sdd/features/DESIGN_NOTIFICATION_SYSTEM.md
/build DESIGN_USER_AUTH.md

# With cross-model judge for code correctness (opt-in, advisory for build)
/build DESIGN_AUTH.md --judge                 # advisory, default openai/gpt-4o
/build DESIGN_AUTH.md --judge=openai/codex-mini    # code-tuned model (cheaper)
/build DESIGN_AUTH.md --judge=strict          # gated on BUILD_REPORT quality

Overview

This is Phase 3 of the 5-phase AgentSpec workflow:

Phase 0: /brainstorm → .claude/sdd/features/BRAINSTORM_{FEATURE}.md (optional)
Phase 1: /define     → .claude/sdd/features/DEFINE_{FEATURE}.md
Phase 2: /design   → .claude/sdd/features/DESIGN_{FEATURE}.md
Phase 3: /build    → Code + .claude/sdd/reports/BUILD_REPORT_{FEATURE}.md (THIS COMMAND)
Phase 4: /ship     → .claude/sdd/archive/{FEATURE}/SHIPPED_{DATE}.md

What Happens

Load .claude/skills/sdd-build/SKILL.md and follow it under the build-agent's non-negotiable policies — decide-never-ask and halt-only-on-CRITICAL-risk, both defined in .claude/agents/workflow/build-agent.md. The skill owns the methodology for Steps 1-6; Step 7 is command-only.

  1. Load Context — DESIGN, DEFINE, CLAUDE.md
  2. Extract Tasks — convert the file manifest to a task list
  3. Order by Dependencies — determine execution order
  4. Execute Each Task — write or delegate, verify, retry (max 3)
  5. Run Full Validation — lint, types, tests across the codebase
  6. Generate Build Report — write BUILD_REPORT and update upstream statuses

Step 7: Optional Judge Pass (--judge)

Runs only if the user invoked with --judge[=MODE]. Cross-model second opinion on the BUILD_REPORT (which references the actual code written), focused on concrete bugs — logic errors, concurrency, security, SQL correctness, IAM/RLS, data loss risks.

Read the full file on GitHub · 138 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 · 138 lines · 16 tokens per session scan A 47534cd978a2

Subscribe to this mod's changes

build is a command published in the GitHub repository luanmorenommaciel/agentspec (244 stars, last pushed 3d ago), licensed MIT. It adds 16 tokens to every session and 1,223 once invoked, about $0.0001 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 2026-09-01.