A repository setup command that creates a selected set of software-lifecycle files and folders, such as an SDLC artifact chain, review rules, or evaluation files. SDLC means the steps used to take software from an idea through planning, building, checking, and release.

Use it to initialize lifecycle documents, verification instructions, review policy, agent-configuration evaluations, or production-metric controls in a Git repository.

It avoids manually inspecting the repository and creating setup files that may already exist. It also lets the user choose which parts to add instead of adding everything.

init — Command for Claude Code by artemnovichkov

Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code

/plugin marketplace add artemnovichkov/skills

Claude Code

/plugin install sdlc

Made for: Claude Code.

Or install sdlc, the plugin that ships this one along with the rest of its 1 skill, 8 commands, 1 agent, 1 hook.

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/artemnovichkov/skills/init/github.svg)](https://agentmods.dev/commands/artemnovichkov/skills/init)

Your own site

<a href="https://agentmods.dev/commands/artemnovichkov/skills/init"><img src="https://agentmods.dev/badge/commands/artemnovichkov/skills/init/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/commands/artemnovichkov/skills/init"><img src="https://agentmods.dev/badge/commands/artemnovichkov/skills/init.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 27 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 766 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	$0.00027	$0.00766
Opus 5	$0.00014	$0.00383
Sonnet 5	$0.00005	$0.00153
Haiku 4.5	$0.00003	$0.00077

Measured yesterday against content hash e54d99d4c994, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

init 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 yesterday.

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/sdlc/commands/init.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.

Initialize the SDLC loop

Set up an artifact-driven lifecycle in the current repository. Add only what the user asks for — do not dump twelve files on them.

Workflow

1. Check the ground

git rev-parse --show-toplevel — abort with an explanation if this is not a git repo.
Check whether sdlc/, REVIEW.md, CLAUDE.md, evals/ already exist. Never overwrite; extend or skip.
Detect the project type (language, build tool, test runner) by reading manifests: Package.swift, *.xcodeproj, package.json, Cargo.toml, go.mod, pyproject.toml.

2. Ask what to enable

Present the pieces and let the user pick (multi-select). Recommend the first two for anyone starting out:

Artifact chain (recommended) — sdlc/intent/, sdlc/spec/, sdlc/plan/ + sdlc/README.md explaining the flow
CLAUDE.md sections (recommended) — verification commands with healthy output, plus a "Things Claude gets wrong" section
Review policy — REVIEW.md at repo root
Config evals — evals/ suite and CI workflow (delegates to /sdlc:evals)
Control bands — sdlc/bands.yaml and watcher (delegates to /sdlc:bands)

3. Create the artifact chain

If selected, create sdlc/intent/, sdlc/spec/, sdlc/plan/, each with a .gitkeep, plus sdlc/README.md describing the chain and which command produces each file. Copy the stage templates from ${CLAUDE_PLUGIN_ROOT}/templates/ into sdlc/templates/ only if the user wants to customise them; otherwise the commands read them from the plugin.

Add sdlc/.lock-tests to .gitignore — it is a local toggle for the test-file guard, not shared state.

4. Extend CLAUDE.md

If selected, append the sections from ${CLAUDE_PLUGIN_ROOT}/templates/claude-md-sections.md, filled in for this repo:

The real build / test / lint commands, discovered from the manifests in step 1. Run each once and paste a trimmed sample of healthy output so future sessions can recognise success.
A quantifiable done-condition ("all tests in X pass", "zero lint warnings").
An empty "Things Claude gets wrong" section with a one-line note on how it gets filled.

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.

yesterday First seen · 51 lines · 27 tokens per session scan A e54d99d4c994

Subscribe to this mod's changes

init is a command published in the GitHub repository artemnovichkov/skills (36 stars, last pushed yesterday), licensed MIT. It adds 27 tokens to every session and 766 once invoked, about $0.0001 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 2026-09-07.

Planning Project management ai codex marketplace mcp plugins

init

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

Initialize the SDLC loop

Workflow

1. Check the ground

2. Ask what to enable

3. Create the artifact chain

4. Extend CLAUDE.md

What this file has done since we first saw it

Other commands, from other repositories

collaborative-spec-builder-existing

speckit.tasks

speckit.taskstoissues

tracker-sync

land

work