onboarding

onboarding is a command for Claude Code from jabrena/plinth. It costs 16 tokens per session (1,235 once invoked), scanned A, original, Apache-2.0.

A repository setup command that establishes root guidance and one OpenSpec project before issue-based work begins. OpenSpec is a project structure for describing and managing proposed changes.

In plain words
What is it for?
Use it to find or create the repository's AGENTS.md guidance and ensure exactly one OpenSpec directory is available before development work.
Why use it?
It prevents issue work from starting with missing instructions or multiple unclear project locations, while preserving existing repository guidance.

Command for Claude Code

Written for Claude Code: argument-hint in frontmatter. Also seen: model in frontmatter; mentions AGENTS.md.

Good fit Use it to find or create the repository's AGENTS.md guidance and ensure exactly one OpenSpec directory is available before development work.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/jabrena/plinth/onboarding
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.

Clone the repo
git clone --depth 1 https://github.com/jabrena/plinth

Made for: Claude Code.

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 onboarding

README.md
[![agentmods](https://agentmods.dev/badge/commands/jabrena/plinth/onboarding/github.svg)](https://agentmods.dev/commands/jabrena/plinth/onboarding)
Your own site
<a href="https://agentmods.dev/commands/jabrena/plinth/onboarding"><img src="https://agentmods.dev/badge/commands/jabrena/plinth/onboarding/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.

agentmods 80×15 button for onboarding

Your own site · 80×15
<a href="https://agentmods.dev/commands/jabrena/plinth/onboarding"><img src="https://agentmods.dev/badge/commands/jabrena/plinth/onboarding.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 16 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,235 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00016 $0.01235
Opus 5.5 $0.00006 $0.00494
Sonnet 5.5 $0.00003 $0.00247
Haiku 4.5 $0.00002 $0.00123

Measured 19d ago against content hash 6736d7606179, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

onboarding 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 19d 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/004-commands-installation/assets/commands/onboarding.md · 85 lines

How it starts

The opening of the file, as written. The whole thing — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.

onboarding

Establish the two repository prerequisites for issue-driven work: root AGENTS.md and exactly one unambiguous OpenSpec project.

Usage

/onboarding

Owner and delegation

  • Owner: @plinth-architect
  • Missing root guidance: delegate to 200-agents-md with the repository root as context.
  • Missing OpenSpec project: delegate standard initialization to 042-planning-openspec with the selected result directory and its parent project root as context.

/onboarding coordinates these existing workflows. It does not duplicate their interactive questions, generation rules, validation, or CLI safeguards.

Prerequisite outcomes

  • Preserve an existing root AGENTS.md unchanged.
  • Recursively discover every directory whose name is exactly openspec; accept and preserve exactly one directory wherever it is located.
  • When no OpenSpec directory exists, ask for a normalized repository-relative result path and offer documentation/openspec as the default.
  • Stop before every mutation when more than one OpenSpec directory exists.

Workflow

  1. Resolve the repository root. Inspect <repository-root>/AGENTS.md and recursively discover the complete set of directories named exactly openspec before starting any delegated workflow or changing any file.
  2. Evaluate OpenSpec ambiguity before mutation.
    • If more than one directory named openspec was found, report every conflicting repository-relative path, identify the ambiguity as technical debt, and stop.
    • Do not start 200-agents-md or 042-planning-openspec, even when root AGENTS.md is missing.
    • If exactly one was found, record and preserve that project without asking for another path or starting initialization.
  3. When no directory named openspec exists, ask the user to select the resulting OpenSpec directory and offer documentation/openspec as the default.
    • Treat the selection as a result directory, not as the project-root argument to openspec init.
    • Normalize the selection before mutation.
    • Reject absolute paths, any normalized path that escapes the repository, and any path whose final segment is not exactly openspec.
    • On invalid input, explain the failure and ask for a valid repository-relative OpenSpec directory or an explicit cancellation.
    • If the user cancels, report cancellation and stop without starting either delegated workflow or changing repository content.
  4. For a valid missing-OpenSpec selection, derive its parent directory as the initialization project root. For example:
    • documentation/openspec -> initialization project root documentation
    • architecture/openspec -> initialization project root architecture Delegate only standard openspec init behavior to 042-planning-openspec, passing both the selected result directory and derived parent project root. Do not pass the result directory itself as the project root. Do not silently choose another path after failure.
  5. Sequence missing prerequisites safely.
    • If both prerequisites are missing, wait for delegated OpenSpec initialization to complete successfully before starting 200-agents-md; never run the interactive delegations concurrently.
    • If OpenSpec initialization fails or is cancelled, do not start 200-agents-md and report that both prerequisites remain incomplete.
    • If OpenSpec initialization succeeds, preserve it even if the later 200-agents-md workflow fails or is cancelled; do not roll back delegated work.
  6. When root AGENTS.md is missing and OpenSpec discovery is unambiguous, delegate its creation to 200-agents-md with the repository root as context. When root AGENTS.md exists, preserve it unchanged and do not start its generation workflow.
  7. Recheck root AGENTS.md and recursively rediscover directories named exactly openspec after delegation. Report each prerequisite as preserved, created, initialized, skipped, failed, cancelled, or blocked, include the OpenSpec path when present, and distinguish full success from partial completion.
  8. On a retry after partial completion, preserve the one initialized OpenSpec project and retry only missing root guidance. When root AGENTS.md and exactly one OpenSpec project already exist, perform no writes, start no delegated workflow, and report the existing OpenSpec location.

Read the full file on GitHub · 85 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.

  1. 19d ago First seen · 85 lines · 16 tokens per session scan A 6736d7606179

Subscribe to this mod's changes

onboarding is a command published in the GitHub repository jabrena/plinth (451 stars, last pushed yesterday), licensed Apache-2.0. It adds 16 tokens to every session and 1,235 once invoked, about $0.0001 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 2026-09-27.