A guided setup tool for the project's configuration files. It asks only the relevant questions when requested, can inspect the environment for likely answers, and can validate settings without writing them.

Use it for a full setup, targeted setup of selected settings, or a dry-run check of configuration. It manages files such as config/tools.json and config/tools.local.json.

It avoids requiring manual editing of configuration files and helps identify missing, invalid, or corrupted settings. It can also resume the command that needed the missing configuration.

configure — Skill for Claude Code by lantisprime/claude-sdlc

Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo

git clone --depth 1 https://github.com/lantisprime/claude-sdlc

agentmods

npx agentmods add skills/lantisprime/claude-sdlc/configure

Made for: Claude Code.

Or install sdlc-plugin, the plugin that ships this one along with the rest of its 18 skills, 16 commands, 10 agents, 4 hooks.

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/skills/lantisprime/claude-sdlc/configure/github.svg)](https://agentmods.dev/skills/lantisprime/claude-sdlc/configure)

Your own site

<a href="https://agentmods.dev/skills/lantisprime/claude-sdlc/configure"><img src="https://agentmods.dev/badge/skills/lantisprime/claude-sdlc/configure/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/lantisprime/claude-sdlc/configure"><img src="https://agentmods.dev/badge/skills/lantisprime/claude-sdlc/configure.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 88 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,103 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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 5.1	$0.00088	$0.02103
Opus 5.5	$0.00035	$0.00841
Sonnet 5.5	$0.00018	$0.00421
Haiku 4.5	$0.00009	$0.00210

Measured 1mo ago against content hash a395db24ebf1, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

configure 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 1mo 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.

skills/configure/SKILL.md · 190 lines

How it starts

The opening of the file, as written. The whole thing — 190 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Configure — Guided Setup

Replace manual config/tools.json editing with a conversational wizard. Power users can still edit files by hand — this is an on-ramp, not a replacement.

Before starting: check env.json flags

Read .claude/sdlc/env.json if it exists.

If config_corrupted: true → skip the normal wizard; go to Layer 3: rebuild below.
If layer_0_pending: true → this is a fresh install; run the full wizard and offer /start on completion.
Otherwise → run normally.

Invocation modes

Full wizard (/configure with no flags): ask all applicable questions.

Scoped mode (/configure --needs tracker.type,tracker.host): ask only the questions that map to the specified keys. Skip everything else. On completion, resume the original command that triggered this invocation.

Dry-run (/configure --check): read config/tools.json and config/tools.local.json, validate against the schema in config/tools.example.json, print a report of what is set, what is null/missing, and what would be asked. No prompts, no writes. Exit when done.

Context-aware defaults

Before asking any question, inspect the environment to pre-select the most likely answer:

Signal	Pre-selected default
`.github/` directory present	GitHub Issues
`git remote -v` contains `github.com`	GitHub Issues
`.linear.yml` present or `linear` on PATH	Linear
`jira` on PATH or `atlassian` in git remote	Jira

User can always override; the default is a keystroke save, not a lock-in.

Question bank (8 questions maximum)

Ask one at a time. Do not front-load.

Q1 — Tracker type

Which issue tracker does this project use? A) GitHub Issues B) GitLab Issues C) Jira D) Linear E) None (pre-selected: <detected default or "None">)

Q2 — Auth token (only if Q1 ≠ None)

Paste your <tracker> auth token. (Stored in config/tools.local.json — never committed.) Skip with Enter to omit; the plugin will accept any URL without host validation.

Read the full file on GitHub · 190 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.

1mo ago First seen · 190 lines · 88 tokens per session scan A a395db24ebf1

Subscribe to this mod's changes

configure is a skill published in the GitHub repository lantisprime/claude-sdlc (3 stars, last pushed 5mo ago), licensed MIT. It adds 88 tokens to every session and 2,103 once invoked, about $0.0004 per session on Opus 5.5. 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.

Claude Code agent-framework agentic-coding agentic-workflow claude-ai claude-code-plugin

moai-workflow-thinking

Sequential Thinking MCP for structured step-by-step analysis via --deepthink flag. Separate from UltraThink which is Claude's native extended reasoning mode. Use for multi-step analysis or architecture decisions.

modu-ai/moai-adk · 43 tokens

xcode-workflows

Xcode build system guidance for xcodebuild operations. Use when building iOS projects, running tests, analyzing build failures, or configuring schemes. Covers build/clean/test operations, interpreting xcodebuild output, and troubleshooting common build errors.

conorluddy/xclaude-plugin · 53 tokens

check-pr

Read-only inspection of a single GitHub PR lifecycle — checks CI, review feedback (threads, review bodies, top-level comments), description sync, and mergeability, and returns PASS or FAIL with per-gate findings. Never invokes the merge button. Use when verifying a PR is ready to merge, polling lifecycle progress…

doodledood/manifest-dev · 83 tokens

goga-define-experience

Define the user experience required to achieve the established product goals and solve the identified problem.

qarium/goga · 6 tokens

goga-define-resolve

Resolve product-level conflicts discovered during the definition process.