A command that checks whether the current software-development phase has met its required exit conditions and moves to the next phase only when those checks pass.

Use it to validate the current phase, see specific failed checks and suggested remedies, generate a report of missing work, and advance the project when the gates pass.

It prevents the workflow from advancing while required documents, checks, or other conditions are missing, and reports blockers when it cannot proceed.

sdlc-next — Command for coding agents by MCKRUZ: A command that checks whether the current software-development phase…

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-next

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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/mckruz/claude-code-sdlc/sdlc-next.svg)](https://agentmods.dev/commands/mckruz/claude-code-sdlc/sdlc-next)

Your own site

<a href="https://agentmods.dev/commands/mckruz/claude-code-sdlc/sdlc-next"><img src="https://agentmods.dev/badge/commands/mckruz/claude-code-sdlc/sdlc-next.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 2,841 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.

Model	Per session	Once invoked
Fable 5	$0.00000	$0.02841
Opus 5	$0.00000	$0.01421
Sonnet 5	$0.00000	$0.00568
Haiku 4.5	$0.00000	$0.00284

Measured 3d ago against content hash 3663b2ecb04b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

sdlc-next 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-next.md · 172 lines

How it starts

The opening of the file, as written. The whole thing — 172 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/sdlc-next — Advance to Next Phase

Run exit gate checks for the current phase and advance to the next phase if all gates pass.

Instructions

Locate state file: Look for .sdlc/state.yaml in the current project directory. If not found, tell the user to run /sdlc-setup first.
Read state: Load .sdlc/state.yaml to determine the current phase.

Run gate checks: Execute the gate checker for the current phase:

uv run --project ${CLAUDE_PLUGIN_ROOT}/scripts ${CLAUDE_PLUGIN_ROOT}/scripts/check_gates.py --state .sdlc/state.yaml

Evaluate results:

If ANY MUST gate fails:
- Display the failure report
- List specific blockers with remediation suggestions
- Do NOT advance the phase
- Generate the phase HTML report anyway (shows what's missing): uv run --project ${CLAUDE_PLUGIN_ROOT}/scripts ${CLAUDE_PLUGIN_ROOT}/scripts/generate_phase_report.py --state .sdlc/state.yaml --phase <phase-number>
- Automatically open the report in the user's default browser (start on Windows, open on macOS, xdg-open on Linux)
- Suggest actions: create missing artifacts, fix incomplete content, etc.
- Offer smart repair: "Would you like me to attempt auto-repair on the fixable issues?" If yes, spawn the gate-repair agent, then re-run gates. See references/smart-repair.md for what's repairable.
If all MUST gates pass (SHOULD/MAY may still have warnings):
- Display success message
- Show any SHOULD/MAY warnings
- Generate the final phase HTML report before advancing:
```
uv run --project ${CLAUDE_PLUGIN_ROOT}/scripts ${CLAUDE_PLUGIN_ROOT}/scripts/generate_phase_report.py \
  --state .sdlc/state.yaml --phase <phase-number>
```
- Automatically open the report in the user's default browser (start on Windows, open on macOS, xdg-open on Linux)
- HITL GATE — Ask for explicit sign-off before advancing: Present the phase summary (what was produced, key decisions made) and ask: "Does this look correct? Shall I advance to Phase N?" Do NOT call advance_phase.py until the human explicitly confirms.
- Optional — capture discipline sign-off(s): After the human confirms the advance, use AskUserQuestion to offer (optionally) recording per-discipline sign-off on this phase's work: "Any discipline sign-offs to record for this phase? (e.g. Design signs the interaction specs, Data signs the data contract, Bizreq signs the business rules.)" This is optional — skipping it advances exactly as before. For each sign-off the human names, capture a Discipline:Section:Name triple; capture the overall signer name too if given. These feed the advance_phase.py invocation in step 6 via --signed-by "<name>" and one --discipline-signoff "Discipline:Section:Name" per sign-off (repeatable). No sign-offs → no flags → byte-identical state. The named human signs; the agent only records what it is told.

Read the full file on GitHub · 172 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.

3d ago First seen · 172 lines · 0 tokens per session scan A 3663b2ecb04b

Subscribe to this mod's changes

sdlc-next is a command published in the GitHub repository MCKRUZ/claude-code-sdlc (4 stars, last pushed 6d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,841 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.

Planning

sdlc-next

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

/sdlc-next — Advance to Next Phase

Instructions

What this file has done since we first saw it

Other commands, from other repositories

git

checklist

clarify

specify

analyze

converge