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 agentmods add settings/christaylorcodes/github-template/settingsgit clone --depth 1 https://github.com/christaylorcodes/GitHub-TemplateGrade A, and why
GitHub-Template 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
{
"permissions": {
"allow": [
"Bash(\"$GH\" issue create --title \"Commit v1.1 changes, verify CI, tag release\" --body \"$\\(cat <<''EOF''\n## Objective\n\nCommit all v1.1 changes, push to GitHub, verify CI workflows pass, and tag the v1.1 release.\n\n## Requirements\n\n- [ ] Stage and commit all changes\n- [ ] Push and verify CI workflows pass \\(test.yml, analyze.yml\\)\n- [ ] Tag v1.1 release\n\n## Context\n\nv1.1 removed legacy Sampler/ModuleBuilder tooling, consolidated on InvokeBuild, added full module template structure, and cleaned up repo layout. Local validation passes: 18/18 tests, 93.1% coverage, 0 analyzer errors.\n\n## Acceptance Criteria\n\n- All CI checks pass on both Ubuntu and Windows\n- v1.1 tag exists on the commit\nEOF\n\\)\" --milestone \"v1.1 Release\" --label \"ai-task,ai-ready\")"
]
}
}
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 · 8 lines scan A 9423fe8eff47
GitHub-Template is a settings file published in the GitHub repository christaylorcodes/GitHub-Template (2 stars, last pushed 2mo 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 settings, from other repositories
supabase
Agent settings declaring 2 hook events (SessionStart, PostToolUse).
claude-cookbooks
Agent settings declaring 2 hook events (SessionStart, PreToolUse).
claude-code-best-practice
Agent settings declaring 30 hook events (PreToolUse, PermissionRequest, PostToolUse, PostToolUseFailure) and 24 allowed tools.
electron
Agent settings declaring 17 allowed tools.
uv
Agent settings declaring 2 hook events (SessionStart, PostToolUse).
ui-ux-pro-max-skill
Agent settings declaring 7 allowed tools.