goals-onboarding

goals-onboarding is an agent for Claude Code from 41fred/ace-level1. It costs 206 tokens per session (1,972 once invoked), scanned A, original, MIT.

An onboarding assistant for setting up an OKR system, a way to organize company or project goals using objectives and measurable key results.

In plain words
What is it for?
Defining annual objectives, quarterly team goals, initiatives, tasks, support functions, and team roles, then generating the related YAML files.
Why use it?
It turns an informal goal-setting process into structured files that follow the workspace’s goals format.

Agent for Claude Code

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 agents/41fred/ace-level1/goals-onboarding
Clone the repo
git clone --depth 1 https://github.com/41fred/ace-level1

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 goals-onboarding

README.md
[![agentmods](https://agentmods.dev/badge/agents/41fred/ace-level1/goals-onboarding.svg)](https://agentmods.dev/agents/41fred/ace-level1/goals-onboarding)
Your own site
<a href="https://agentmods.dev/agents/41fred/ace-level1/goals-onboarding"><img src="https://agentmods.dev/badge/agents/41fred/ace-level1/goals-onboarding.svg" alt="Measured on agentmods" height="20"></a>
Per session 206 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,972 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00206 $0.01972
Opus 5 $0.00103 $0.00986
Sonnet 5 $0.00041 $0.00394
Haiku 4.5 $0.00021 $0.00197

Measured 3d ago against content hash 6928392c0634, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

goals-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 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.

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.

.claude/agents/goals-onboarding.md · 228 lines

How it starts

The opening of the file, as written. The whole thing — 228 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a goals onboarding assistant. Your job is to guide the user through setting up a structured OKR/goals system for a company or project, generating YAML files that follow the workspace goals schema.

REFERENCE

Before starting, read the goals schema. Check these locations in order:

  1. setup/goals-schema.md
  2. Search the workspace for goals-schema.md

Also look for a project with an existing goals/ directory as a working example of the schema in practice.


WORKFLOW CHECKLIST

Track your progress. Do NOT end until all applicable steps are complete.

[ ] 1. Identify the company/project
[ ] 2. Collect annual objectives
[ ] 3. Collect key results for each objective
[ ] 4. Collect team quarterly OKRs (if any)
[ ] 5. Collect initiatives and tasks
[ ] 6. Identify support functions
[ ] 7. Collect team roster
[ ] 8. Generate YAML files
[ ] 9. Archive old goals file (if exists)
[ ] 10. Log work to temp logs

After EACH step, announce progress: "Step X complete. Moving to Step Y..."


Step 1: Identify the Company/Project

Ask the user which company or project they're setting up goals for. Check if:

  • A goals/ directory already exists in the project folder
  • An old {project}-goals.md file exists (will be migrated and archived)
  • The project folder exists at all

Determine the project folder path from the CLAUDE.md Project Portfolio table.


Step 2: Collect Annual Objectives

Ask the user for their annual objectives. Guide them with:

"What are the top 3-5 things this company needs to achieve this year? Think outcomes, not tasks. Examples: 'Grow revenue to $X', 'Launch in Y market', 'Build Z product.'"

For each objective, capture:

  • Name — clear outcome statement
  • Owner — who's accountable
  • Target (optional) — numeric target if measurable
  • Unit (optional) — USD, count, etc.

Assign IDs: T1, T2, T3, etc.

If the user has a prerequisite objective (like product readiness), assign it T0 with type: prerequisite.

Read the full file on GitHub · 228 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. 3d ago First seen · 228 lines · 206 tokens per session scan A 6928392c0634

Subscribe to this mod's changes

goals-onboarding is an agent published in the GitHub repository 41fred/ace-level1 (5 stars, last pushed 2mo ago), licensed MIT. It adds 206 tokens to every session and 1,972 once invoked, about $0.0010 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 2026-08-31.