sdlc-build

sdlc-build is a command for coding agents from saitarrun/Devforge-ai. It costs 50 tokens per session (2,158 once invoked), scanned A, original, Apache-2.0.

A build command for the second phase of a software-development lifecycle, the process used to plan, build, and verify software. It reads a feature handoff, implements work in slices, and then runs end-to-end tests.

In plain words
What is it for?
Use it to build feature slices across data, APIs, interfaces, and tests, optionally involve a user-experience designer, and run final quality-assurance tests.
Why use it?
It turns an approved implementation plan into staged development work with checks between slices.

Command

Part of the devforge-ai plugin — 28 skills, 17 commands, 13 agents 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/saitarrun/devforge-ai/sdlc-build
Clone the repo
git clone --depth 1 https://github.com/saitarrun/Devforge-ai

Or install devforge-ai, the plugin that ships this one along with the rest of its 28 skills, 17 commands, 13 agents.

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 sdlc-build

README.md
[![agentmods](https://agentmods.dev/badge/commands/saitarrun/devforge-ai/sdlc-build.svg)](https://agentmods.dev/commands/saitarrun/devforge-ai/sdlc-build)
Your own site
<a href="https://agentmods.dev/commands/saitarrun/devforge-ai/sdlc-build"><img src="https://agentmods.dev/badge/commands/saitarrun/devforge-ai/sdlc-build.svg" alt="Measured on agentmods" height="20"></a>
Per session 50 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,158 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 $0.00050 $0.02158
Opus 5 $0.00025 $0.01079
Sonnet 5 $0.00010 $0.00432
Haiku 4.5 $0.00005 $0.00216

Measured 3d ago against content hash fdb07f04adf8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

sdlc-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 3d 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/sdlc-build.md · 258 lines

How it starts

The opening of the file, as written. The whole thing — 258 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/sdlc-build — Phase 2: Build

Implements the feature slice-by-slice using the tracer bullet pattern. Each slice is a vertical cut through all required layers (schema → API → UI → tests), verified before the next begins.

Agents Invoked

  • ux-designer — once before the slice loop (only when has_ui: true)
  • fullstack-engineer — once per slice (Slice 0 + all feature slices)
  • qa-engineer — once after all slices complete
  • Ralph Loop skill applied at each fullstack-engineer invocation

STEP 1: Read Handoff (Clean Context Window)

Read ./projects/<feature>/handoffs/plan-handoff.md before doing anything else.

This document contains the distilled context from the Plan phase — grill-summary decisions, scope.json snapshot, and the slice decomposition. Loading it first ensures the Build phase starts with a bounded, fresh context window rather than carrying the entire Plan conversation forward.


STEP 2: Read scope.json

Read ./projects/<feature>/scope.json to extract:

  • capability_flags.has_ui — controls whether ux-designer runs
  • capability_flags.has_auth, has_mobile, has_data_pipeline — inform fullstack-engineer context
  • slices[] — the ordered build plan: [{id, name, type, layers, linear_id?}]

The first slice is always "type": "prefactor". All subsequent slices are "type": "feature".


STEP 3: UX Design (scope-gated on has_ui)

If has_ui: true:

Invoke ux-designer once before any slice begins:

Agent: ux-designer
Context:
  - ./projects/<feature>/grill-summary.md
  - ./projects/<feature>/scope.json (full slices list)
  - ./projects/<feature>/handoffs/plan-handoff.md

Output: ./projects/<feature>/docs/ux-design.md
  - Wireframes for all UI slices
  - Component specs and design tokens
  - User flow diagrams
  - Interaction states (loading, error, empty, success)

ux-designer runs exactly once — not per slice. All subsequent fullstack-engineer invocations reference ux-design.md.

If has_ui: false: Skip ux-designer entirely. No invocation, no artifact.

Read the full file on GitHub · 258 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. 3d ago First seen · 258 lines · 50 tokens per session scan A fdb07f04adf8

Subscribe to this mod's changes

sdlc-build is a command published in the GitHub repository saitarrun/Devforge-ai (5 stars, last pushed 20d ago), licensed Apache-2.0. It adds 50 tokens to every session and 2,158 once invoked, about $0.0003 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.