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 bootstrapgit 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/bootstrap)<a href="https://agentmods.dev/skills/timbogp/timbogp-marketplace/bootstrap"><img src="https://agentmods.dev/badge/skills/timbogp/timbogp-marketplace/bootstrap/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/bootstrap"><img src="https://agentmods.dev/badge/skills/timbogp/timbogp-marketplace/bootstrap.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 | $0.00148 | $0.02041 |
| Opus 5 | $0.00074 | $0.01020 |
| Sonnet 5 | $0.00030 | $0.00408 |
| Haiku 4.5 | $0.00015 | $0.00204 |
Grade A, and why
bootstrap 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 11d 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 — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Bootstrap a learning sub-project
This skill mints a new sub-project under the agentic-study-environment harness. A sub-project is a self-contained folder where a learner works through a single topic with the agent as tutor, scaffolded by the harness's conventions.
When to use
The user wants to start studying something new. They might say "bootstrap a project to learn TASEP", "create a sub-project for Spanish vocabulary", "set up a learning project for the seam carving paper", or similar. The signal is: a topic they want to learn, an intent to study it under the harness.
This skill does NOT run a teaching session — that's start-session. It only sets up the scaffolding.
What you need from the user
Required (ask if missing — do not invent):
- a sub-project name (becomes the directory name, e.g.
seam-carver,spanish-b2,tasep) - a one-line learning goal that captures what the user wants to learn
Optional (use if supplied; do not prompt for them — they can be filled later via the sub-project's AGENTS.md):
- a Domain — controls which overlay applies during sessions. Known values:
coding,speech-therapy(synonym:logopedics),legal-documents(synonyms:official-documents,public-documents),academic-research(synonyms:research,scholarship),study(the neutral default), or any user-supplied custom value. If unset, the sub-project falls back to the neutral default. - a Language — BCP 47 tag (e.g.
de,es,fr) overriding the conversational language for chat replies inside this sub-project. Default is English unless an optional.studyenv/AGENTS.md(or.studyenv/CLAUDE.md) sets otherwise. Structural tokens (status legends, field names, trigger words) stay in English regardless — see../../reference/conventions.mdfor the exact rules. - Tools & Materials — anything the user already knows they'll work with (a language + version for coding, a textbook, a notation convention, …).
- Tracking —
global(default) orlocal-only.globalregisters the sub-project in the cross-project.studyenv/PROGRESS.mdtracker (the umbrella mode).local-onlykeeps just the sub-project's ownPROGRESS.mdand skips the cross-project tracker entirely — for a lone learning project where no global index is wanted. Default toglobalwhen unstated; do not prompt. See../../reference/conventions.md→ Tracking scope. - A note that source materials are already in place — controls the starting status of the sub-project.
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.
- 11d ago First seen · 82 lines · 148 tokens per session scan A fd5ba0a62fda
bootstrap is a skill published in the GitHub repository TimboGP/timbogp-marketplace (3 stars, last pushed 2mo ago), licensed MIT. It adds 148 tokens to every session and 2,041 once invoked, about $0.0007 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.
examples
Provide Phoenix, LiveView, Ecto, OTP, or Oban examples. Use when asked for sample code, a walkthrough, a proper implementation, or expected workflow output. Pair with domain skills. NOT for debugging, direct changes, best-practice advice, or audits.