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.
git clone --depth 1 https://github.com/tobihagemann/turboWrote 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/plugins/tobihagemann/turbo/claude)<a href="https://agentmods.dev/plugins/tobihagemann/turbo/claude"><img src="https://agentmods.dev/badge/plugins/tobihagemann/turbo/claude/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/plugins/tobihagemann/turbo/claude"><img src="https://agentmods.dev/badge/plugins/tobihagemann/turbo/claude.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
turbo 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.
What it actually says
{
"name": "turbo",
"displayName": "Turbo",
"description": "A human-gated agentic software factory: you decide what to build and judge the result, while skills shape, build, polish, and ship the change, and learn from it.",
"author": {
"name": "Tobias Hagemann",
"url": "https://github.com/tobihagemann"
},
"homepage": "https://github.com/tobihagemann/turbo",
"repository": "https://github.com/tobihagemann/turbo",
"license": "MIT",
"types": "./types/index.d.ts"
}
What it installs
The manifest is a name and a version. 71 skills travel with it, and installing the plugin installs all of them — 3,190 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill draft-plan A 49 tokens
- Skill resolve-pr-feedback A 49 tokens
- Skill consult-codex A 49 tokens
- Skill implement-backlog A 46 tokens
- Skill investigate A 46 tokens
- Skill update-dependencies A 40 tokens
- Skill review-code A 48 tokens
- Skill smoke-test A 52 tokens
- Skill assess-technical-debt A 50 tokens
- Skill codex-exec A 47 tokens
- Skill create-test-plan A 56 tokens
- Skill create-threat-model A 48 tokens
- Skill backlog A 50 tokens
- Skill exploratory-test A 50 tokens
- Skill peer-review A 46 tokens
- Skill review-plan A 41 tokens
- Skill changelog-rules A 18 tokens
- Skill consult-oracle A 42 tokens
- Skill github-voice A 31 tokens
- Skill interpret-feedback A 42 tokens
- Skill recall-session A 45 tokens
- Skill reply-to-pr-threads A 48 tokens
- Skill review-dependencies A 39 tokens
- Skill ship A 47 tokens
- Skill explain-this A 54 tokens
- Skill fetch-pr-comments A 38 tokens
- Skill contribute A 43 tokens
- Skill create-issue A 49 tokens
- Skill reply-to-pr-conversation A 41 tokens
- Skill pick-next-issue A 53 tokens
- Skill pr A 47 tokens
- Skill stage A 39 tokens
- Skill commit-staged-push A 44 tokens
- Skill stage-commit-push A 50 tokens
- Skill polish-code A 56 tokens
- Skill evaluate-findings A 40 tokens
- Skill refine-plan A 49 tokens
- Skill simplify-code A 47 tokens
- Skill apply-findings A 40 tokens
- Skill discuss-change A 46 tokens
- Skill simplify-docs A 48 tokens
- Skill test-run-rules A 32 tokens
- Skill create-project-skills A 45 tokens
- Skill implement A 46 tokens
- Skill write-skill A 44 tokens
- Skill dream A 51 tokens
- Skill split-and-ship A 42 tokens
- Skill handoff A 49 tokens
- Skill implement-plan A 48 tokens
- Skill preview A 51 tokens
- Skill prototype A 46 tokens
- Skill code-style A 38 tokens
- Skill quick-finalize A 45 tokens
- Skill resolve-open-items A 45 tokens
- Skill teach-change A 44 tokens
- Skill triage-backlog A 52 tokens
- Skill finalize A 47 tokens
- Skill plan A 45 tokens
- Skill run-checks A 51 tokens
- Skill survey-patterns A 43 tokens
- Skill user-experience A 46 tokens
- Skill create-changelog A 53 tokens
- Skill review-pr A 46 tokens
- Skill update-changelog A 42 tokens
- Skill simplify-all A 48 tokens
- Skill commit-rules A 22 tokens
- Skill implement-findings A 37 tokens
- Skill self-improve B 45 tokens
- Skill commit-staged A 34 tokens
- Skill stage-commit A 43 tokens
- Skill context-level A 47 tokens
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 Changed 4d0d45543e44
- 4d ago First seen · 14 lines scan A 785a89c02323
turbo is a plugin published in the GitHub repository tobihagemann/turbo (420 stars, last pushed today), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 2026-11-08.
turbo compared with plugins from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| turbotobihagemann/turbo | Plugin | 420 | today | MIT | A | — | Claude Code |
| pm-agentopsmohitagw15856/pm-claude-skills | Plugin | 1.5k | today | MIT | A | — | Claude Code |
| liquid-glassstormaref/LiquidGlassSkill | Plugin | 20 | 2mo ago | MIT | A | — | Claude Code |
| running-coachColinEberhardt/claude-running-coach | Plugin | 33 | 5mo ago | MIT | A | — | Claude Code |
| context-optimizationviktorbezdek/skillstack | Plugin | 15 | 5mo ago | MIT | A | — | Claude Code |
| adaptoadaptocms/adapto-cms-agent-skills | Plugin | 1 | 3mo ago | MIT | A | — | Claude Code |
| humanizerblader/humanizer | Plugin | 68k | 3d ago | MIT | A | — | Claude Code |