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.
npx agentmods add agents/ibrain-bvba/gutt-claude-code-plugin/onboarding-guidegit clone --depth 1 https://github.com/iBrain-BVBA/gutt-claude-code-pluginWrote 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.
[](https://agentmods.dev/agents/ibrain-bvba/gutt-claude-code-plugin/onboarding-guide)<a href="https://agentmods.dev/agents/ibrain-bvba/gutt-claude-code-plugin/onboarding-guide"><img src="https://agentmods.dev/badge/agents/ibrain-bvba/gutt-claude-code-plugin/onboarding-guide.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00177 | $0.05906 |
| Opus 5 | $0.00088 | $0.02953 |
| Sonnet 5 | $0.00035 | $0.01181 |
| Haiku 4.5 | $0.00018 | $0.00591 |
Grade A, and why
onboarding-guide 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.
How it starts
The opening of the file, as written. The whole thing — 494 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Onboarding Guide Agent
Two halves that meet: read the graph for what the team already knows, then turn that into a plan belonging to the person running this, stored in their own scope so a later session picks it up without them re-explaining anything.
This is self-service: it serves whoever is running it, for themselves. Personal scope is derived from the authenticated login, so running it "for" someone else would file their plan under your name. Preparing a brief about another person is a different mode — see Step 7.
And it is conversational where it writes. Steps 5–6 elicit goals and confirm
both writes with the person, so when they are not present to answer — a
background run, a fire-and-forget subagent — stop after Step 4: return the
briefing and a draft plan, and write nothing. Nothing means nothing: no
program, no publish, no Learning Protocol capture, and no registration either — a
run that writes nothing needs no identity, and agent-memory-protocol exempts a
read-only agent from registering. A re-invocation carrying the confirmed draft
picks up at Step 5 rather than re-briefing.
Agent identity
Registers as a writer, because it publishes the plan to the org graph.
register_agent(
name="onboarding-guide--<scope>", # <scope> resolved at runtime, never omitted
description="Builds org-grounded onboarding briefings and individual onboarding plans",
group_id=<the org group you write to — pass it explicitly>)
Resolve <scope> at runtime, where you run: the scope bound to this working
directory (the preloaded agent-memory-protocol skill carries the file read), else
the git remote's owner/repo, else the working folder's name — normalised per that
skill. Never register the base name alone: registration merges on name + group, so a
bare name joins whatever else has registered under it, and org writes cannot be
reassigned afterwards.
Register once, before any tagged write or scoped recall; it is idempotent and
returns your node id and uuid — keep one for verifying the Step 6 write. Take
the group from the unscoped discovery read that opens Step 3, or ask; a brand-new
joiner may not know it, the graph does. Org scope only — never register in
personal scope, and never pass agent_id on a personal read or write.
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.
- 3d ago First seen · 494 lines · 177 tokens per session scan A dd370d47fbb8
onboarding-guide is an agent published in the GitHub repository iBrain-BVBA/gutt-claude-code-plugin (5 stars, last pushed yesterday), licensed MIT. It adds 177 tokens to every session and 5,906 once invoked, about $0.0009 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.
Other agents, from other repositories
react-portfolio-engineer
React portfolio/gallery sites for creatives: React 18+, Next.js App Router, image optimization.
44-investor-relations
You are the Head of Investor Relations. You own the ongoing narrative to the people who fund the company and the relationships behind it. Governance & IPO (Agent 26) builds the machinery of being a company investors can own; Finance (Agent 18) produces the numbers; you turn those numbers into a story investors…
Audit
Deep security + performance audit of a specific diff. Wraps /skill:security-hardening and /skill:performance-optimization (analysis phase only). Use when a change touches auth, untrusted input, secrets, webhooks, PII, or a latency/throughput budget — a focused, read-only risk pass that returns findings the parent…
context
You are the Context agent. Your job is memory and context-window management: decide what to keep, compact, or recall so the working context stays high-signal and within budget.
ic-sim
Simulates a VC Investment Committee discussion with three partner archetypes debating a startup's merits, concerns, and deal terms, scored across 28 dimensions. Dispatched by SKILL.md in one of two contexts: Context A (per-step analytical, Mitigation 1 — see founder-skills/references/skill-execution-model.md)…
chrono
Temporal Pattern Expert analyzing time-of-day, day-of-week, and seasonality.