sdlc

A command that runs a software development life cycle (SDLC)—the stages used to plan, build, check, release, and maintain software—in five phases with approval points between them.

In plain words
What is it for?
Use it to coordinate feature work such as authentication or OAuth, rerun one phase, and organize planning, implementation, testing, security, release, and operations artifacts.
Why use it?
It keeps work from jumping straight from an idea to code and preserves handoff documents between phases.

Command

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
Clone the repo
git clone --depth 1 https://github.com/saitarrun/Devforge-ai
Per session 42 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,320 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 $0.00042 $0.01320
Opus 5 $0.00021 $0.00660
Sonnet 5 $0.00008 $0.00264
Haiku 4.5 $0.00004 $0.00132

Measured 2d ago against content hash 36810237931a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

sdlc 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/sdlc.md · 115 lines

How it starts

The opening of the file, as written. The whole thing — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Master SDLC Orchestrator

This command runs the complete Software Development Lifecycle end-to-end with 5 phases, explicit approval gates between each phase, and handoff documents to keep context windows bounded.

Usage

/sdlc "build a user authentication system"
/sdlc "add OAuth login" --from Plan --to Build
/sdlc --phase Build  # Re-run Build phase in isolation

Phases

The orchestrator runs agents sequentially across 5 phases:

  1. Plan/sdlc-plan (product-manager: grill interview + scope.json + PRD + issues)
  2. Build/sdlc-build (ux-designer [if has_ui] + fullstack-engineer × slices + qa-engineer)
  3. Verify/sdlc-verify (security-engineer + performance-engineer [if needs_performance_audit])
  4. Ship/sdlc-ship (devops-engineer)
  5. Operate/sdlc-operate (sre-engineer + data-engineer [if has_data_pipeline])

9 agents total (product-manager, ux-designer, fullstack-engineer, qa-engineer, security-engineer, performance-engineer, devops-engineer, sre-engineer, data-engineer)

Process

  1. Parse feature request
  2. Create ./projects/<feature-name>/ with docs/, handoffs/ subdirectories
  3. Run Plan phase → product-manager interviews + produces scope.json + PRD
  4. GATE: "Ready to start Build?" → on confirm: run /handoff → handoffs/plan-handoff.md → invoke /sdlc-build
  5. Build phase completes → GATE: "Ready to start Verify?" → on confirm: run /handoff → handoffs/build-handoff.md → invoke /sdlc-verify
  6. Verify phase completes → GATE: "Ready to Ship?" → on confirm: run /handoff → handoffs/verify-handoff.md → invoke /sdlc-ship
  7. Ship phase completes → GATE: "Ready to Operate?" → on confirm: run /handoff → handoffs/ship-handoff.md → invoke /sdlc-operate
  8. Compile final summary

Phase Transition Flow

/sdlc-plan
  └─ [GATE: "Ready to start Build?"]
       └─ /handoff → handoffs/plan-handoff.md
            └─ /sdlc-build
                 └─ [GATE: "Ready to start Verify?"]
                      └─ /handoff → handoffs/build-handoff.md
                           └─ /sdlc-verify
                                └─ [GATE: "Ready to Ship?"]
                                     └─ /handoff → handoffs/verify-handoff.md
                                          └─ /sdlc-ship
                                               └─ [GATE: "Ready to Operate?"]
                                                    └─ /handoff → handoffs/ship-handoff.md
                                                         └─ /sdlc-operate

Read the full file on GitHub · 115 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 · 115 lines · 42 tokens per session scan A 36810237931a

Subscribe to this mod's changes

sdlc is a command published in the GitHub repository saitarrun/Devforge-ai (5 stars, last pushed 19d ago), licensed Apache-2.0. It adds 42 tokens to every session and 1,320 once invoked, about $0.0002 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.