start

A command that starts or resumes a software development lifecycle workflow, meaning an organised process for planning and delivering code changes. It detects project settings, records the task, and creates an initial scope and plan.

In plain words
What is it for?
Use it when starting a new coding task, re-enabling the workflow, or continuing work in a project that already has an active plan.
Why use it?
It gives a project a defined starting point instead of leaving task details and planning scattered. It can also restore the workflow after it has been suspended.

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/lantisprime/claude-sdlc/start
Clone the repo
git clone --depth 1 https://github.com/lantisprime/claude-sdlc
Per session 101 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 301 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 $0.00101 $0.00301
Opus 5 $0.00051 $0.00151
Sonnet 5 $0.00020 $0.00060
Haiku 4.5 $0.00010 $0.00030

Measured 2d ago against content hash 54cb9cf0ea6a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

start 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/start.md · 14 lines

What it actually says

Invoke the start skill. The skill reads the marker state and routes accordingly:

  • Fresh install (.enabled absent, .suspended absent): Step 0 auto-detects config, Step 1 creates .enabled, Step 2 takes a one-sentence task description, Step 3 auto-generates scope.md and a draft plan, Step 4 shows the "what this armed" summary. Hands off to /plan for review and sign-off.

  • Suspended (.suspended present): calls hooks/suspend-snapshot.sh verify, shows per-plan reconciliation output (HIGH/LOW severity), accepts or rejects each changed plan, proposes REQ supersession for accepted HIGH-severity plans, then re-enables enforcement.

  • Already enabled (.enabled present): hands off to /plan to start or continue a task.

Power users with an active signed plan can skip directly to /plan.

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 · 101 tokens per session scan A 54cb9cf0ea6a

Subscribe to this mod's changes

start is a command published in the GitHub repository lantisprime/claude-sdlc (3 stars, last pushed 4mo ago), licensed MIT. It adds 101 tokens to every session and 301 once invoked, about $0.0005 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.