onboarding

onboarding is an agent for coding agents from Espenandreass1/agentslice. It costs 0 tokens per session (416 once invoked), scanned A, original, MIT.

A project-startup guide for coding agents. It tells an agent which planning files to read, what context applies to its role, and which approval steps govern the work.

In plain words
What is it for?
Use it when an agent joins or resumes a project. It helps agents prepare for planning, building, testing, or release work.
Why use it?
It prevents agents from starting with incomplete or outdated project information. It also keeps workflow status and approvals in the right source of truth.

Agent

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/espenandreass1/agentslice/onboarding
Clone the repo
git clone --depth 1 https://github.com/Espenandreass1/agentslice

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/agents/espenandreass1/agentslice/onboarding.svg)](https://agentmods.dev/agents/espenandreass1/agentslice/onboarding)
Your own site
<a href="https://agentmods.dev/agents/espenandreass1/agentslice/onboarding"><img src="https://agentmods.dev/badge/agents/espenandreass1/agentslice/onboarding.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 416 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 $0.00000 $0.00416
Opus 5 $0.00000 $0.00208
Sonnet 5 $0.00000 $0.00083
Haiku 4.5 $0.00000 $0.00042

Measured 3d ago against content hash a63c6faebb75, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 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.

kit/docs/agents/onboarding.md · 36 lines

What it actually says

Agent Onboarding

Start with the active preflight

Read AGENT_RULES.md, docs/planning/active-context.md, docs/planning/workflow-state.md, docs/planning/current-slice.md, and docs/planning/checkpoint.md. The checkpoint is a compact handoff summary; the state file alone controls the phase and approval fields.

Add only your role context

  • Planning: vision, tech stack, live next slices.
  • Build: approved spec and coding rules.
  • QA: approved spec, changed files, QA plan, and one directly relevant earlier report only if needed.
  • Release: current spec, QA report, changelog.

Use docs/archive/README.md and targeted search when a concrete historical question remains. Do not bulk-read folders or logs.

Gates

The workflow remains: slice approval → spec approval → independent QA PASS/PASS WITH NOTES → human release approval. The quick-fix lane stays inside those gates.

Active-document discipline

  • active-context.md: product summary, active constraints, current slice/spec, next gate, QA policy, nearest priorities; 180 lines maximum.
  • workflow-state.md: phase, approvals, next action, valid phases, hard stops only.
  • next-slices.md: one to three living candidates.
  • decisions.md: active decisions/constraints only.
  • changelog.md: one short user-facing release entry.
  • checkpoint.md: under 80 lines; authoritative links, checks, risks, next action, and per-slice telemetry. Archive it when superseded.

Efficient execution

  • Focused acceptance tests and relevant domain regressions are the QA default. A full suite needs a stated trigger in qa-plan.md.
  • Do not parallelize by default; independent QA/review is the normal exception.
  • Report passed commands as command plus result. For failures, show only the relevant excerpt, impact, and next action.

See migrating-to-active-context.md for existing projects.

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 · 36 lines · 0 tokens per session scan A a63c6faebb75

Subscribe to this mod's changes

onboarding is an agent published in the GitHub repository Espenandreass1/agentslice (4 stars, last pushed 8d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 416 tokens. 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.