adev:init

An interactive setup wizard for creating or checking the project's shared context directory, which stores information agents use to understand the codebase.

In plain words
What is it for?
Use it to initialize a project, prepare an existing codebase with extra analysis, inspect an existing setup, or initialize a workspace containing several repositories.
Why use it?
It gives a new or existing project a consistent starting structure and lets you preview or choose which parts to set up.

Skill for Claude CodeCodex

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 skills/agentic-development/adev-plugin/init
Any agent
npx skills add agentic-development/adev-plugin --skill init
Clone the repo
git clone --depth 1 https://github.com/agentic-development/adev-plugin

Made for: Claude Code, Codex.

Per session 87 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 12,307 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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 $0.00087 $0.12307
Opus 5 $0.00044 $0.06153
Sonnet 5 $0.00017 $0.02461
Haiku 4.5 $0.00009 $0.01231

Measured 2d ago against content hash 02d30adbf4bf, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

adev:init scanned grade B with 1 finding 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

- `~/.claude/settings.json` → `enabledPlugins` for globally enabled plugins
providers/codex/skills/init/SKILL.md · 1,120 lines

How it starts

The opening of the file, as written. The whole thing — 1,120 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Initialize Context Index

Interactive setup wizard for the Agentic Development Framework. Walks through each context layer one at a time, explains what it does, and lets the user opt in or skip.

Arguments

  • No arguments: interactive wizard (detects greenfield vs. existing setup automatically)
  • --brownfield: adds reverse-chartering, ADR archaeology, and coverage analysis
  • --dry-run: shows what would be created without writing any files
  • --workspace: initialize a workspace root that aggregates multiple child repos under one adev-workspace.yaml

Load Skill Extensions

Load Skill Extensions: Load any skill extension instructions before proceeding:

adev skill-ext load --skill init

If the output is not __NONE__, incorporate it as additional standing instructions that apply to this skill's entire execution. Frame it as: "The following skill extension instructions apply to this invocation (source: installed domain extensions and/or project-level overrides)." If the output is __NONE__, continue normally.

Behavior by Project State

Detecting First Run vs. Diagnostic Mode

The presence of .context-index/ does NOT mean the project has been configured. adev install (the CLI step that runs before /adev:init) always scaffolds a minimal .context-index/ from templates — it creates manifest.yaml, constitution.md, the directory tree, and stamps adev_version — then tells the user to run /adev:init next. So on a fresh install the directory always exists, but it is still in pristine template state (unconfigured).

Decide the mode by whether the context index has actually been configured, not by whether the directory exists:

  1. .context-index/ is absent → First Run (onboarding wizard).
  2. .context-index/ exists but is still in pristine template state → First Run (onboarding wizard). Treat it as unconfigured when ANY of these hold:
    • manifest.yaml is missing, or still contains the template placeholders {{ project_name }} / {{ project_description }}.
    • constitution.md is missing, or still contains the template placeholder {{ project_name }} or the unfilled principle stubs (1. ..., 2. ...). In this case do NOT report "existing project" or run the health check — the install merely scaffolded the skeleton; the user has not configured anything yet. Proceed with the onboarding wizard below (files already present are overwritten/filled in as the user answers each step).
  3. .context-index/ exists AND is configured (placeholders replaced with real values) → Diagnostic Mode (health check).

Read the full file on GitHub · 1,120 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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 · 1,120 lines · 87 tokens per session scan B 02d30adbf4bf

Subscribe to this mod's changes

adev:init is a skill published in the GitHub repository agentic-development/adev-plugin (11 stars, last pushed 2d ago), licensed MIT. It adds 87 tokens to every session and 12,307 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens