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/miXshift/mx-claude-pluginWrote 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/mixshift/mx-claude-plugin/mixshift-ai)<a href="https://agentmods.dev/plugins/mixshift/mx-claude-plugin/mixshift-ai"><img src="https://agentmods.dev/badge/plugins/mixshift/mx-claude-plugin/mixshift-ai/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/mixshift/mx-claude-plugin/mixshift-ai"><img src="https://agentmods.dev/badge/plugins/mixshift/mx-claude-plugin/mixshift-ai.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
mixshift-ai 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 yesterday.
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.
The source is not reproduced here
A licence we could not identify
The repository carries a LICENSE file, but it is custom or dual enough that GitHub cannot name it and neither can this catalogue. Unknown terms are not permission, so the body is not copied here. Read the licence at the source and decide for yourself.
What it installs
The manifest is a name and a version. 34 skills, 1 hook travel with it, and installing the plugin installs all of them — 4,850 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill mx-max-report A 191 tokens
- Skill mx-amazon-dsp A 221 tokens
- Skill mx-brand-context A 214 tokens
- Skill mx-amazon-ads A 198 tokens
- Skill mx-amazon-amc A 214 tokens
- Skill mx-daily-health-check A 70 tokens
- Skill mx-data-explore A 134 tokens
- Skill mx-amazon-inbound A 181 tokens
- Skill mx-asin-target-negation A 119 tokens
- Skill mx-walmart-ads A 198 tokens
- Skill mx-amazon-shelf A 160 tokens
- Skill mx-budget-balance A 133 tokens
- Skill mx-keyword-bid-health A 62 tokens
- Skill mx-max-forecast A 225 tokens
- Skill mx-monthly-report A 104 tokens
- Skill mx-search-term-negation A 40 tokens
- Skill mx-auth-service-setup A 180 tokens
- Skill mx-feedback A 198 tokens
- Skill mx-phrase-negative-discovery A 66 tokens
- Skill mx-portfolio-quick-scan A 112 tokens
- Skill mx-runaway-spend-check A 69 tokens
- Skill mx-scheduled-task A 166 tokens
- Skill mx-search-term-harvest A 52 tokens
- Skill mx-walmart-retail A 223 tokens
- Skill mx-featured-offer-check A 135 tokens
- Skill mx-ppc-relevance-check A 134 tokens
- Skill mx-search-term-data-pull A 58 tokens
- Skill mx-update A 110 tokens
- Skill mx-welcome A 49 tokens
- Skill mx-help A 167 tokens
- Skill mx-share-skill A 112 tokens
- Skill mx-auth-login B 167 tokens
- Skill mx-amazon-retail C 209 tokens
- Skill mx-amazon-report C 179 tokens
- Hook SessionStart A not measured
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.
- yesterday Changed e87a894b22ff
- 8d ago Changed c0c1a14671fb
- 15d ago Changed 7e09c65bb573
- 22d ago Changed 95c617a6bf0f
- 29d ago Changed be00b303f669
- 1mo ago Changed 77f8e3443e7c
- 1mo ago Changed c92c72522491
- 1mo ago Changed afdebf7f4406
- 1mo ago Changed · +9 lines 960a7412c702
- 2mo ago First seen · 10 lines scan A bdc230c6b63d
mixshift-ai is a plugin published in the GitHub repository miXshift/mx-claude-plugin (2 stars, last pushed yesterday), with no licence file. 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 2026-08-31.
mixshift-ai compared with plugins from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| mixshift-aimiXshift/mx-claude-plugin | Plugin | 2 | yesterday | none | A | — | Claude Code |
| humanizerblader/humanizer | Plugin | 66k | 11d ago | MIT | A | — | Claude Code |
| claude-plugins-official marketplaceanthropics/claude-plugins-official | Plugin | 46k | yesterday | Apache-2.0 | A | — | Claude Code |
| themes-examplegoogle-gemini/gemini-cli | Plugin | 109k | today | Apache-2.0 | A | — | Gemini CLI |
| nextjsvercel/next.js | Plugin | 143k | today | MIT | A | — | Claude Code |
| knowledge-work-plugins marketplaceanthropics/knowledge-work-plugins | Plugin | 35k | yesterday | Apache-2.0 | A | — | Claude Code |
| code-modernizationanthropics/claude-plugins-official | Plugin | 46k | yesterday | Apache-2.0 | A | — | Claude Code |