sdlc-data

A command that documents the data a feature uses, how ready that data is, and how it should be tracked through the system. It also classifies personally identifiable information, meaning data that can identify a person.

In plain words
What is it for?
Use it inside an SDLC project or standalone to produce a data contract, readiness assessment, and data lineage and audit design.
Why use it?
It makes data risks, missing inputs, and audit needs visible while the feature is being designed. This can clarify the feature's scope and turn readiness problems into decisions to track.

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/mckruz/claude-code-sdlc/sdlc-data
Clone the repo
git clone --depth 1 https://github.com/MCKRUZ/claude-code-sdlc
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,113 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 $0.00000 $0.01113
Opus 5 $0.00000 $0.00557
Sonnet 5 $0.00000 $0.00223
Haiku 4.5 $0.00000 $0.00111

Measured 2d ago against content hash 63a25bd2be20, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

sdlc-data 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-data.md · 74 lines

How it starts

The opening of the file, as written. The whole thing — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/sdlc-data — Author the Data Contract, Readiness, and Lineage for a Feature

Give Data a first-class drafting seat: the data contract (PII-classified), the data-readiness assessment, and the lineage / audit design for a feature or spec. It sharpens Scope, surfaces the PII that drives risk tier, and turns readiness gaps into tracked decisions. Interview-driven like /sdlc-coach: the data-analyst agent assesses what's there, asks focused questions, and drafts as answers arrive. It proposes; a named human decides (the One Rule). Works inside an SDLC project or standalone.

Instructions

  1. Resolve context:

    • Workflow mode (default): .sdlc/state.yaml exists. Read the feature-brief / spec Scope and any data-* artifacts; outputs land in .sdlc/artifacts/02-design/data/.
    • Standalone mode (--repo <path>, or no .sdlc/ found): operate on the given repo with provisional context; write to --output (default alongside the repo) and note the missing context in the artifact headers.
  2. Assess what exists: Read the feature-brief's Data touchpoints section, any success-criteria baseline, and the current data artifacts — which fields are named, which sources are known, what is still unclassified.

  3. Run the interview: Spawn the data-analyst agent (Data discipline). It runs the coach-style dialogue — which fields the feature reads or writes, their sources and types, which are PII or customer-linked, whether the data is actually available and complete, and how it flows end to end (lineage + retention). It drafts three artifacts from the templates in templates/phases/02-design/data/:

    • data-contract.md — the field table with an explicit PII? column.
    • data-readiness.md — availability / completeness / quality, with gaps flagged (advisory).
    • lineage-audit.md — source → transform → sink flow with retention and audit points.
  4. Confirm PII and route readiness gaps with the human:

Read the full file on GitHub · 74 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 · 74 lines · 0 tokens per session scan A 63a25bd2be20

Subscribe to this mod's changes

sdlc-data is a command published in the GitHub repository MCKRUZ/claude-code-sdlc (4 stars, last pushed 4d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,113 tokens. 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.