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 swisspra/On_Board --skill onboardgit clone --depth 1 https://github.com/swisspra/On_BoardWrote 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/swisspra/on_board/onboard)<a href="https://agentmods.dev/skills/swisspra/on_board/onboard"><img src="https://agentmods.dev/badge/skills/swisspra/on_board/onboard/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/swisspra/on_board/onboard"><img src="https://agentmods.dev/badge/skills/swisspra/on_board/onboard.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 | $0.00032 | $0.00375 |
| Opus 5.5 | $0.00013 | $0.00150 |
| Sonnet 5.5 | $0.00006 | $0.00075 |
| Haiku 4.5 | $0.00003 | $0.00038 |
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 2d 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.
What it actually says
On Board
On Board is a shared multi-agent memory server. It keeps project state under
.agent-mem/ and is reached over MCP under the server key agent-memory.
Choose the matching path
Install, configure, repair, update, or diagnose On Board → read references/install.md.
It runs in order: pick the project and the MCP client, reuse or install the
onboard-memory-mcp runtime, write only the selected client's project config,
then report honest status (configured, or still waiting for restart/trust).
Installation is not memory initialization. Do not call memory_onboard,
memory_bootstrap, or memory_init as a setup step or a health check, and do
not create or migrate .agent-mem/ while installing. Offer to start the project
afterwards — starting is a separate, explicit request.
Already connected and initialized, doing project work → read references/protocol.md.
It carries the session protocol: join, read the briefing, write after meaningful
actions, checkpoint, and hand off before you stop. If the project has no
.agent-mem/ yet, or the On Board tools are not visible in this session, go back
to references/install.md.
Primary commands
Install or refresh this skill for a project. Project scope by default; the skills CLI manages client links and update tracking:
npx skills add swisspra/On_Board --skill onboard
Update the skill itself (this does not upgrade linked projects' runtimes):
npx skills update -p onboard
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 2d ago First seen · 45 lines · 32 tokens per session scan A 4e4e87323e9c
onboard is a skill published in the GitHub repository swisspra/On_Board (4 stars, last pushed 2d ago), licensed Apache-2.0. It adds 32 tokens to every session and 375 once invoked, about $0.0001 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 2026-10-27.
Other skills, from other repositories
memory-distill
Destilliert rohe Staging-Inbox-Bullets (staging/captured.md) in bleibende, getypte Memory-Dateien. Verwende diesen Skill, wenn der User 'distill', 'Staging aufräumen', 'Inbox abarbeiten', 'Memory verdichten' sagt oder nach einem Ingest-Lauf oder Staging-Nag.
memory-sync
Audits and updates local agent memory. Scans configured coding folders, registers or ignores new projects, writes PROJECTS.md, syncs your Agent injection. Use when the user says Bestandaufnahme, memory sync, neues Projekt, inventory, Projekte updaten, register project, or wants agents to know a new repo path.
context-engineering
Optimizes agent context setup. Use when starting a new session, when agent output quality degrades, when switching between tasks, or when you need to configure rules files and context for a project.
agent-memory-discipline
Rules for when an agent should recall from long-term memory before acting and when it should save decisions, corrections and failures afterwards. Works with any memory backend.
memory
Persist and retrieve agent memory across sessions — recall via the three-stage protocol (structure route → semantic search → navigation fallback), read via memoryload, see the wiki structure via memorybrowse, write well-placed pages via memorywrite (including section-level append/rewrite), maintain via memorycurate.…
memory-dream
Curate the workspace memory wiki as its appointed orchestrator. Trigger on a Cloud-scheduled Dream task or a user's direct curation request. Inspect candidates for orphan leaves, near-duplicates, stale pages, remote conflicts and oversized hubs; browse the graph, cluster leaves into INDEX/hub/leaf structure, maintain…