onboard

onboard is a command for Claude Code from dosatos/minimise. It costs 11 tokens per session (358 once invoked), scanned A, original, MIT.

A command for starting a work session by reading the latest project handoff, then planning implementation through the mini job tool.

In plain words
What is it for?
Orienting an agent, creating and reviewing a YAML plan, starting a mini job, and checking its progress and results.
Why use it?
It restores recent context and keeps implementation work organized in a reviewed job.

Command for Claude Code

Part of the minimise plugin — 6 skills, 3 commands 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 commands/dosatos/minimise/onboard
Clone the repo
git clone --depth 1 https://github.com/dosatos/minimise

Made for: Claude Code.

Or install minimise, the plugin that ships this one along with the rest of its 6 skills, 3 commands.

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 onboard

README.md
[![agentmods](https://agentmods.dev/badge/commands/dosatos/minimise/onboard.svg)](https://agentmods.dev/commands/dosatos/minimise/onboard)
Your own site
<a href="https://agentmods.dev/commands/dosatos/minimise/onboard"><img src="https://agentmods.dev/badge/commands/dosatos/minimise/onboard.svg" alt="Measured on agentmods" height="20"></a>
Per session 11 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 358 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 $0.00011 $0.00358
Opus 5 $0.00005 $0.00179
Sonnet 5 $0.00002 $0.00072
Haiku 4.5 $0.00001 $0.00036

Measured 4d ago against content hash e6ffadf5a7ba, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

onboard 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 4d 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/commands/onboard.md · 46 lines

What it actually says

Read the latest project handoff to orient yourself:

cat worklogs/handoffs/session-latest.md

Execution rule: delegate to mini job, don't implement inline

For any real implementation work this session, delegate it to a mini job rather than editing files directly in this conversation. Reserve direct edits for trivial one-liners and for mini-blocked changes (schema migrations, internal refactors mini can't invoke).

Two reasons this is the default:

  1. Keeps this context clean. Execution/implementation churn (file dumps, test output, agent narration) stays inside the job, not in the orchestrating session — so this context stays about decisions, not diffs.
  2. Quality gates come free. A job run through the /minimise:review-plan skill gets its plan reviewed before execution — the gates are already wired, you just have to use the path.

The flow:

# 1. Write a plan.yaml (scratch plans -> worklogs/scratch/)
# 2. Review it (adds the quality gate):  invoke the /minimise:review-plan skill
mini job new --plan worklogs/scratch/<plan>.yaml
mini job start <job-id>
mini job status <job-id>          # watch progress
mini job results <job-id>         # logs + diffs when done

Context loaded. $ARGUMENTS

If you'd like to continue with a specific task, just tell me what to work on!

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. 4d ago First seen · 46 lines · 11 tokens per session scan A e6ffadf5a7ba

Subscribe to this mod's changes

onboard is a command published in the GitHub repository dosatos/minimise (11 stars, last pushed 15d ago), licensed MIT. It adds 11 tokens to every session and 358 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 2026-08-30.