agentic-init

agentic-init is a skill for Claude Code, Codex from Jarroslav/agentic-os. It costs 127 tokens per session (15,334 once invoked), scanned A, original, Apache-2.0.

An installer that adds the agentic-os process layer to a repository. It interviews the user about roles and approval levels, generates stack-specific agents and templates, records its progress, and verifies the result.

In plain words
What is it for?
Scaffolding governed multi-agent projects, registering dependencies, generating instructions for the detected technology stack, and checking the installed setup.
Why use it?
It gives a new multi-agent setup a documented, repeatable installation process that can resume after interruption.

Skill for Claude CodeCodex

Part of the agentic-os plugin — 4 skills 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 skills/jarroslav/agentic-os/agentic-init
Any agent
npx skills add Jarroslav/agentic-os --skill agentic-init
Clone the repo
git clone --depth 1 https://github.com/Jarroslav/agentic-os

Made for: Claude Code, Codex.

Or install agentic-os, the plugin that ships this one along with the rest of its 4 skills.

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 agentic-init

README.md
[![agentmods](https://agentmods.dev/badge/skills/jarroslav/agentic-os/agentic-init.svg)](https://agentmods.dev/skills/jarroslav/agentic-os/agentic-init)
Your own site
<a href="https://agentmods.dev/skills/jarroslav/agentic-os/agentic-init"><img src="https://agentmods.dev/badge/skills/jarroslav/agentic-os/agentic-init.svg" alt="Measured on agentmods" height="20"></a>
Per session 127 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 15,334 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 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 $0.00127 $0.15334
Opus 5 $0.00063 $0.07667
Sonnet 5 $0.00025 $0.03067
Haiku 4.5 $0.00013 $0.01533

Measured 3d ago against content hash 85ba8b60ee3a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agentic-init scanned grade A 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 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.

Reads agent configuration directorieslowAgent snooping

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

`TARGET/.claude/settings.json` (create the file if absent) via deep-merge:

Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.

plugins/agentic-os/skills/agentic-init/SKILL.md · 889 lines

How it starts

The opening of the file, as written. The whole thing — 889 lines — stays where its author put it; the contents beside it link to each section on GitHub.

agentic-init — the installer

You scaffold a governed multi-agent architecture into the target repo (the current working directory's git root, TARGET below). Everything you copy, render, or generate is journaled so an interrupted run resumes and a re-run is idempotent.

Conventions (read once, apply everywhere)

  • PLUGIN = the agentic-os plugin root (${CLAUDE_PLUGIN_ROOT} when set; otherwise the directory two levels above this SKILL.md). It contains templates/, generators/, presets/, manifest/.

  • AGENTIC_OS_VERSION = "version" from PLUGIN/.claude-plugin/plugin.json.

  • Journal = TARGET/.agentic/agentic-os/install.json. Shape:

    {
      "agentic_os_version": "<AGENTIC_OS_VERSION>",
      "stack_discovery": { "...": "the structured record from generators/stack-discovery.md — see templates/VARIABLES.md § The stack-fact record" },
      "answers": { "<interview key>": "<value>" },
      "phase": "preflight|interview|dependencies|scaffold|generate|verify|done",
      "files": {
        "<repo-relative path>": {
          "sha256": "<hex of the file as written>",
          "template": "<template ID, gen/* slot, or 'derived'>",
          "owner": "managed|user|generated",
          "origin": "plugin|adopted-existing|generated"
        }
      },
      "follow_ups": ["<human-readable follow-up items>"]
    }
    

    Update the journal after every phase (and after every file write in Phase 4/5). sha256 of a file: shasum -a 256 <file> | cut -d' ' -f1.

  • Owner semantics: managed = agentic-os wrote it and may overwrite it on upgrade when unmodified; user = pre-existed or user-declined — never touched again; generated = produced by a generator subagent — upgrades offer regeneration, never overwrite.

  • Origin semantics: origin records where a file came from, which owner alone cannot express. Assets adopted from a fleet the repo already had carry owner: "user" with origin: "adopted-existing" — they are inputs to verification and never destinations for scaffolding or upgrade.

  • Rendering (registry: PLUGIN/templates/VARIABLES.md): substitution of {{VAR}} — no logic in templates; every conditional lives here. Files without .tmpl are copied verbatim. How you substitute depends on the file type:

    • .py.tmpl and .json.tmpl — escape every scalar. Substitute json.dumps(value, ensure_ascii=False)[1:-1]: the value with ", \, and control characters (newlines included) escaped, and no surrounding quotes. The template already supplies the quotes — do not strip them, and do not hand-escape. Mandatory in every position: whole literal, interpolated literal, triple-quoted block, comment. Templates quote with " only; json.dumps does not escape '.

Read the full file on GitHub · 889 lines

Files

What ships with it

2 files 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. 3d ago First seen · 889 lines · 0 tokens per session scan A 85ba8b60ee3a

Subscribe to this mod's changes

agentic-init is a skill published in the GitHub repository Jarroslav/agentic-os (0 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 127 tokens to every session and 15,334 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

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

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 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