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.
/plugin marketplace add osouthgate/agent-plus-skillsnpx agentmods add plugins/osouthgate/agent-plus-skills/github-remotegit clone --depth 1 https://github.com/osouthgate/agent-plus-skillsGrade A, and why
github-remote 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.
What it actually says
{
"name": "github-remote",
"description": "Read-first wrapper around the GitHub REST API \u2014 one-call PR/branch overviews (state + checks + reviews + runs), name-resolved PRs and issues, --wait on async flows, --json on lists. Zero token leakage. One write: pr comment.",
"version": "0.5.0",
"author": {
"name": "Oliver Southgate",
"url": "https://github.com/osouthgate"
},
"homepage": "https://github.com/osouthgate/agent-plus-skills",
"repository": "https://github.com/osouthgate/agent-plus-skills",
"license": "MIT",
"keywords": [
"github",
"devops",
"pull-requests",
"ci",
"actions",
"incident-triage",
"code-review"
],
"agent_plus_version": ">=0.7",
"refresh_handler": {
"command": "github-remote whoami --json",
"timeout_seconds": 10,
"identity_keys": ["login", "default_org"],
"failure_mode": "soft"
}
}
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 First seen · 29 lines scan A 883ed6ca1cd2
github-remote is a plugin published in the GitHub repository osouthgate/agent-plus-skills (2 stars, last pushed 3mo ago), 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 2026-08-31.
Other plugins, from other repositories
github-talent-marketplace
Plugin marketplace listing 1 plugin: github-talent-mcp.
github-talent-mcp
Search, score, and rank GitHub developers for technical recruiting. Exposes 9 tools: plansearch, searchdevelopers, getdeveloperprofile, rankcandidates, scoreagainstjd, comparecandidates, bulkscore, generateoutreach, getrepocontributors.
markifact
Run Google Ads, Meta Ads, GA4, Shopify, and 20+ more platforms from Claude. 1000+ operations with human-in-the-loop on every write.
alibabacloud-agent-toolkit
Plugin marketplace listing 3 plugins: alibabacloud-core, alibabacloud-spec-ops, alibabacloud-ecs-ops.
alibabacloud-spec-ops
Alibaba Cloud AI Ops Plugin - Infrastructure operations workflow with intelligent planning, validation, and execution powered by MCP tooling.
neatcontext
Save Claude Code work as reusable, domain-aware context.