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 skills add Maless88/Roadboard --skill onboardinggit clone --depth 1 https://github.com/Maless88/RoadboardWrote 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/skills/maless88/roadboard/onboarding)<a href="https://agentmods.dev/skills/maless88/roadboard/onboarding"><img src="https://agentmods.dev/badge/skills/maless88/roadboard/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.
<a href="https://agentmods.dev/skills/maless88/roadboard/onboarding"><img src="https://agentmods.dev/badge/skills/maless88/roadboard/onboarding.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00080 | $0.00650 |
| Opus 5.5 | $0.00032 | $0.00260 |
| Sonnet 5.5 | $0.00016 | $0.00130 |
| Haiku 4.5 | $0.00008 | $0.00065 |
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 1mo 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 — 28 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project onboarding (into RoadBoard)
You onboard a project that already has its repo cloned locally (the clone path is in your context under "Repo del progetto"). Populate RoadBoard only via its MCP tools — never parallel stores.
First, refresh tool knowledge
Call initial_instructions once to get the current RoadBoard MCP operating manual before using other tools.
Steps
- Analyze the repo (read-only): identify stack, entry points, modules/services, dependencies, structure and conventions. Use Serena for code navigation (see the
serena-navskill) — do not grep for symbols. - Discovery: summarize stack + structure (what is built, wired, stubbed).
- Baseline memory: save an architectural baseline as a RoadBoard memory entry (
create_memory_entry, typearchitecture). - Architecture / Atlas: map workspace/modules/services and their dependencies into RoadBoard via
ingest_architecture(one-shot) OR the granular tools:create_architecture_repository→create_architecture_node(per app/module/service) →create_architecture_edge(depends_on, etc.) →create_architecture_link/create_architecture_annotationfor semantic context. - Plan/phase: create the onboarding phase and tasks (
create_phase,create_task) reflecting current state and next steps; record key decisions (create_decision) when relevant. - Render the project CLAUDE.md (Layer 3 / project facts): write a
CLAUDE.mdat the repo root with local dev orientation — stack, layout, run/build/test commands, entry points, conventions, gotchas, and the RoadBoard project id. This is a render of the RoadBoard summary, not a separate store: derive it from what you just put in RoadBoard. Do not put task/phase/decision data in it. - Handoff: write a handoff memory entry with the next steps (navigation, state, gaps).
Hard rules
- RoadBoard is the single source of truth for project management (tasks, phases, memory, decisions, architecture): every such artifact goes in via MCP, not in side files.
- The per-repo
CLAUDE.mdis the ONLY allowed local file, and only as dev-orientation rendered from RoadBoard — never as a competing store of project-management data. - Read/analyze the repo freely; never commit — code commits happen only on the user's explicit request.
- Never claim you onboarded / created something without having actually called the tool.
- Report a concise summary of what you created (phase, tasks, Atlas nodes/edges, memory, CLAUDE.md).
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.
- 1mo ago First seen · 28 lines · 80 tokens per session scan A 7340902b34d6
onboarding is a skill published in the GitHub repository Maless88/Roadboard (3 stars, last pushed 2mo ago), licensed MIT. It adds 80 tokens to every session and 650 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
change-management
Create and transition ServiceNow change requests (normal/standard/emergency), change tasks, affected CIs, approval routing, CAB scheduling, and conflict detection across maintenance windows.
sla-management
Configure ServiceNow SLAs — contractsla definitions with start/stop/pause/cancel conditions, tasksla status checks, breach escalation, business-hours schedules, and compliance-rate aggregation.
vendor-management
Manage ServiceNow vendors and contracts — corecompany vendor records, astcontract with renewal alerts, astcontractsla performance tracking, vendorriskassessment scoring, and vendor scorecards.
virtual-agent
Build ServiceNow Virtual Agent — syscstopic conversations, topic blocks (text/prompt/script/decision/handoff), NLU utterances and custom entities, quick replies, and KB/incident integration scripts.
agile-development
ServiceNow Agile Development 2.0 — the rmteam → rmsprint → rmstory → rmepic model, the state and point values ServiceNow actually accepts, how a story is attached to a sprint, and the reporting tools (board, burndown, velocity, capacity, standup, retrospective).
coordinate
Coordinate multiple agents for a complex multi-domain project using PM planning, parallel agent spawning, and QA review.