build

A build-phase command for implementing an approved software design. It coordinates the planned code changes, tests, formatting, security checks, and links to requirements or tickets.

In plain words
What is it for?
Use it to turn an approved design into code, unit tests, and deployment or pipeline changes, followed by human sign-off.
Why use it?
It limits changes to the agreed scope and prevents editing code without a plan. It also catches secrets and requires tests for modified functions.

Command

Part of the sdlc-plugin plugin — 19 skills, 16 commands, 10 agents, 4 hooks shipped together

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/lantisprime/claude-sdlc/build
Clone the repo
git clone --depth 1 https://github.com/lantisprime/claude-sdlc

Or install sdlc-plugin, the plugin that ships this one along with the rest of its 19 skills, 16 commands, 10 agents, 4 hooks.

Per session 19 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 234 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 $0.00019 $0.00234
Opus 5 $0.00010 $0.00117
Sonnet 5 $0.00004 $0.00047
Haiku 4.5 $0.00002 $0.00023

Measured 2d ago against content hash 989a2bb43b42, 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.

commands/build.md · 20 lines

What it actually says

Invoke the build skill. Prerequisite: .claude/sdlc/gates/design-<task-slug>.md.

The skill coordinates with surgical-edit, minimal-code, and security-review. Hooks enforce:

  • plan-gate — no Edit/Write without a plan
  • work-item-validation — builds reference a REQ ID / ticket / signed CR
  • diff-scope-check — only plan-listed files are modified
  • adjacent-function-detector — only plan-listed functions are modified
  • modified-code-test-gate — unit tests added only for functions actually modified
  • format-on-write — formatter runs on every changed file
  • secret-scan — blocks secrets committed to the diff

Produces: code + unit tests + deployment/pipeline deltas.

On completion, invoke the gate-signoff skill to capture the human sign-off via chat and write .claude/sdlc/gates/build-<task-slug>.md.

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 · 20 lines · 19 tokens per session scan A 989a2bb43b42

Subscribe to this mod's changes

build is a command published in the GitHub repository lantisprime/claude-sdlc (3 stars, last pushed 4mo ago), licensed MIT. It adds 19 tokens to every session and 234 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 2026-08-31.