sdlc-coach

sdlc-coach is a command for coding agents from MCKRUZ/claude-code-sdlc. It costs 0 tokens per session (555 once invoked), scanned A, original, MIT.

A conversational guide for the current stage of a software-development lifecycle. It reads the project’s saved documents and asks questions based on what is missing or unfinished.

In plain words
What is it for?
Use it to start or continue planning work, identify incomplete documents and decisions, and develop the required phase artifacts through questions and dialogue.
Why use it?
Rigid checklists do not always fit the project’s current situation. Coaching mode adapts the conversation to existing documents, unresolved decisions, and the requirements of the current phase.

Command

Part of the claude-code-sdlc plugin — 9 skills, 28 commands, 20 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/mckruz/claude-code-sdlc/sdlc-coach
Clone the repo
git clone --depth 1 https://github.com/MCKRUZ/claude-code-sdlc

Or install claude-code-sdlc, the plugin that ships this one along with the rest of its 9 skills, 28 commands, 20 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-coach

README.md
[![agentmods](https://agentmods.dev/badge/commands/mckruz/claude-code-sdlc/sdlc-coach.svg)](https://agentmods.dev/commands/mckruz/claude-code-sdlc/sdlc-coach)
Your own site
<a href="https://agentmods.dev/commands/mckruz/claude-code-sdlc/sdlc-coach"><img src="https://agentmods.dev/badge/commands/mckruz/claude-code-sdlc/sdlc-coach.svg" alt="Measured on agentmods" height="20"></a>
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 555 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 $0.00555
Opus 5 $0.00000 $0.00278
Sonnet 5 $0.00000 $0.00111
Haiku 4.5 $0.00000 $0.00056

Measured 4d ago against content hash 3bf66e5fed89, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

sdlc-coach 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 4d 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-coach.md · 51 lines

How it starts

The opening of the file, as written. The whole thing — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/sdlc-coach — Interactive Phase Coaching

Start or continue a coaching conversation for the current SDLC phase. Coaching mode uses adaptive dialogue instead of rigid step lists to guide the user through phase requirements.

Instructions

  1. Read state: Load .sdlc/state.yaml to determine the current phase.

  2. Assess state: Read all artifacts in .sdlc/artifacts/{NN}-{phase-name}/:

    • Which artifacts exist?
    • Which are complete vs. still containing placeholders?
    • What decisions remain unmade?
  3. Load context:

    • Read references/conversational-coaching.md for coaching patterns and diagnostic questions
    • Read frozen layers from .sdlc/context/layers/ for prior phase context
    • Read the phase definition from phases/{NN}-{phase-name}.md for requirements
  4. Begin coaching dialogue based on state:

    No artifacts exist → Opening mode:

    • Greet with phase goal in one sentence
    • Ask the first 2-3 diagnostic questions from the phase's "Opening" section
    • Wait for responses before generating any artifacts

    Some artifacts exist → Progress mode:

    • Acknowledge what's done ("I see your problem statement and constraints are in place")
    • Identify the most important gap
    • Ask targeted questions from the phase's "Progress Check" section

    All required artifacts exist → Ready mode:

    • Confirm all artifacts are present
    • Ask the "Ready Check" questions to validate confidence
    • Suggest running /sdlc-gate when the user is satisfied
  5. Respond adaptively to each user interaction:

    • User provides information → generate or update the relevant artifact, then ask the next question
    • User asks a question → answer from phase context and profile, then guide back to the gap
    • User is stuck → offer 2-3 concrete suggestions based on the state assessment
    • User wants to skip ahead → warn about gate requirements, explain what's needed
  6. Track through artifacts: The coaching conversation itself is ephemeral — artifacts are the record. After each significant exchange, update the relevant artifact so progress is preserved across sessions.

Read the full file on GitHub · 51 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. 4d ago First seen · 51 lines · 0 tokens per session scan A 3bf66e5fed89

Subscribe to this mod's changes

sdlc-coach is a command published in the GitHub repository MCKRUZ/claude-code-sdlc (4 stars, last pushed 7d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 555 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.