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 TimboGP/timbogp-marketplace --skill onboard-sessiongit clone --depth 1 https://github.com/TimboGP/timbogp-marketplaceWrote 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/timbogp/timbogp-marketplace/onboard-session)<a href="https://agentmods.dev/skills/timbogp/timbogp-marketplace/onboard-session"><img src="https://agentmods.dev/badge/skills/timbogp/timbogp-marketplace/onboard-session/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/timbogp/timbogp-marketplace/onboard-session"><img src="https://agentmods.dev/badge/skills/timbogp/timbogp-marketplace/onboard-session.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 | $0.00194 | $0.01297 |
| Opus 5 | $0.00097 | $0.00648 |
| Sonnet 5 | $0.00039 | $0.00259 |
| Haiku 4.5 | $0.00019 | $0.00130 |
Grade A, and why
onboard-session 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 12d 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 — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Begin an onboarding session
This skill begins a bracketed onboarding session: getting up to speed on an existing artifact — a codebase, a document corpus, a body of papers — that the user did not author. The artifact is the source material; the goal is a working mental model and the confidence to make changes, not learning a topic from first principles.
Onboarding is one of the harness's four core session types, alongside theory, practice, and role-play. The other three are proposed and run through start-session; onboarding gets its own skill because its shape differs enough to warrant it — a read-only pass over an artifact outside the usual source-materials flow, its own three-phase protocol, and its own artifact tree under work/onboarding/.
When to use
The user wants to get familiar with something someone else built or wrote — a new job's codebase, an open-source project, a teammate's service, an inherited body of papers, a legal corpus. Phrases like "onboard me on this codebase", "walk me through this repo", "help me get up to speed on X", or "I just joined this project" should match.
If the user has not bootstrapped a sub-project yet, redirect them to the bootstrap skill first.
If the user instead wants theory, practice, or role-play, redirect to start-session — this skill only runs onboarding.
What to read before doing anything else
Before proposing or conducting anything, load context — the same up-front reads as start-session:
- The harness's optional
.studyenv/AGENTS.mdif present, otherwise.studyenv/CLAUDE.mdif present (for cross-project conventions and any globalLanguage:), and.studyenv/PROGRESS.md. Both are optional context; if either is missing, continue without it. - The sub-project's
.studyenv/<name>/AGENTS.md, falling back to.studyenv/<name>/CLAUDE.mdfor older projects (forDomain:,Language:, goals, Tools & Materials), and.studyenv/<name>/PROGRESS.md(for what's been covered and at what status). - The sub-project's
.studyenv/<name>/ai-agent-materials/— especiallycurriculum.md, which may already name anonboardingtopic entry — andwork/onboarding/map.mdif a prior onboarding session left one (so you resume where the last one left off, rather than re-surveying from scratch). - If the sub-project declares
Domain:, load the matching overlay at../../domains/<domain>.md(relative to this SKILL.md). The overlay supplies the four onboarding parameters below; if noDomain:is set, the generic protocol applies over a flat corpus.
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.
- 12d ago First seen · 50 lines · 194 tokens per session scan A e7a59aef44fd
onboard-session is a skill published in the GitHub repository TimboGP/timbogp-marketplace (3 stars, last pushed 2mo ago), licensed MIT. It adds 194 tokens to every session and 1,297 once invoked, about $0.0010 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 skills, from other repositories
explain
Explain what a piece of code does — a specific file, class, or method in close detail, or a user-facing flow as a concise system overview. What it does and why, not whether it's good.
gan-zhong-xue
A learning workflow that makes an AI explain code changes through questions, evidence, and underlying principles. It is designed to help developers understand work they asked an AI to do, rather than merely accept the result.
qector-educator
Teaching and documentation content for quantum error correction with QECTOR: beginner-to-advanced tutorials, ELI5 explanations of syndromes / decoders / parity checks, Tanner-graph visual explanations, and local Markdown teaching material. Load for explanations, course material, or documentation generation.
kb-friendica
Background knowledge about Friendica, the federated social networking platform (Facebook alternative). Covers Friendica's history and lineage (Mistpark 2010, Friendika, Friendica, the Red Matrix/Hubzilla fork), its multi-protocol architecture (ActivityPub, DFRN, Diaspora protocol simultaneously), the DFRN protocol…
learn-from-fix
Capture Elixir/Ecto/LiveView lessons and Hex API rules. Use after corrections or when asked to document learning, record a lesson, prevent a fixed mistake, or remember package guidance with --library.
elixir-idioms
OTP/BEAM patterns and Elixir idioms — GenServer, Supervisor, Task, Registry, pattern matching, with chains, pipes. Use when designing processes or debugging BEAM issues.