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/srbryers/slope/settingsgit clone --depth 1 https://github.com/srbryers/slopeGrade A, and why
slope 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 2d 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 — 233 lines — stays where its author put it; the contents beside it link to each section on GitHub.
{
"hooks": {
"PreToolUse": [
{
"hooks": [
{
"type": "command",
"command": "\"$CLAUDE_PROJECT_DIR\"/.claude/hooks/slope-guard.sh explore",
"timeout": 10,
"statusMessage": "SLOPE: Suggest checking codebase index before deep exploration"
}
],
"matcher": "Read|Glob|Grep|Edit|Write"
},
{
"hooks": [
{
"type": "command",
"command": "\"$CLAUDE_PROJECT_DIR\"/.claude/hooks/slope-guard.sh hazard",
"timeout": 10,
"statusMessage": "SLOPE: Warn about known issues in file areas being edited"
},
{
"type": "command",
"command": "\"$CLAUDE_PROJECT_DIR\"/.claude/hooks/slope-guard.sh scope-drift",
"timeout": 10,
"statusMessage": "SLOPE: Warn when editing files outside claimed ticket scope"
},
{
"type": "command",
"command": "\"$CLAUDE_PROJECT_DIR\"/.claude/hooks/slope-guard.sh stale-flows",
"timeout": 10,
"statusMessage": "SLOPE: Warn when editing files belonging to a stale flow definition"
},
{
"type": "command",
"command": "\"$CLAUDE_PROJECT_DIR\"/.claude/hooks/slope-guard.sh claim-required",
"timeout": 10,
"statusMessage": "SLOPE: Warn when editing code without an active sprint claim"
}
],
"matcher": "Edit|Write"
},
{
"hooks": [
{
"type": "command",
"command": "\"$CLAUDE_PROJECT_DIR\"/.claude/hooks/slope-guard.sh subagent-gate",
"timeout": 10,
"statusMessage": "SLOPE: Enforce model selection on Explore/Plan subagents"
}
],
"matcher": "Agent"
},
{
"hooks": [
{
"type": "command",
"command": "\"$CLAUDE_PROJECT_DIR\"/.claude/hoWhat 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.
- 2d ago First seen · 233 lines scan A ccc4c16b2807
slope is a settings file published in the GitHub repository srbryers/slope (6 stars, last pushed 2d 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.