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 commands/gf-labs/ramp/upgit clone --depth 1 https://github.com/gf-labs/rampWrote 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/commands/gf-labs/ramp/up)<a href="https://agentmods.dev/commands/gf-labs/ramp/up"><img src="https://agentmods.dev/badge/commands/gf-labs/ramp/up.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00028 | $0.12407 |
| Opus 5 | $0.00014 | $0.06203 |
| Sonnet 5 | $0.00006 | $0.02481 |
| Haiku 4.5 | $0.00003 | $0.01241 |
Grade C, and why
up scanned grade C with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Strips warnings and disclaimersmediumAnti-refusal
Omitting safety caveats hides risk from the user and is a common jailbreak preamble.
- Mode A: never lecture about Claude Code features without demonstrating them immediately through building Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
!`FIRST=$(echo "$ARGUMENTS" | awk '{print tolower($1)}'); if [ -n "$FIRST" ] && { [ -f "$HOME/.claude/ramp/schemas/$FIRST.md" ] || [ -f ".claude/knowledge-graphs/schemas/$FIRST.md" ]; }; then TOPIC="$FIRST"; else TOPIC=" How it starts
The opening of the file, as written. The whole thing — 690 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Auto-collected context
User-provided context: $ARGUMENTS
Working directory: !pwd
Git repos in this directory:
!find . -maxdepth 2 -name ".git" -type d 2>/dev/null | sed 's|/.git||' | sort
Current repo root:
!git rev-parse --show-toplevel 2>/dev/null || echo "NOT_IN_GIT_REPO"
Top-level contents:
!ls -1 2>/dev/null
Tech stack signals:
!{ [ -f package.json ] && echo "Node/JS: $(python3 -c "import sys,json; d=json.load(open('package.json')); print(d.get('name','?'),'—',d.get('description',''))" 2>/dev/null || cat package.json | head -5)"; [ -f Cargo.toml ] && echo "Rust: $(grep '^name' Cargo.toml | head -1)"; [ -f pyproject.toml ] && echo "Python: $(grep '^name' pyproject.toml | head -1)"; [ -f go.mod ] && echo "Go: $(head -1 go.mod)"; [ -f Makefile ] && echo "Makefile present: $(grep '^[a-zA-Z].*:' Makefile | head -6 | awk -F: '{print $1}' | tr '\n' ' ')"; [ -f pom.xml ] && echo "Java/Maven detected"; [ -f build.gradle ] && echo "Java/Gradle detected"; } 2>/dev/null || echo "No common stack files detected"
README (first 80 lines):
!head -80 README.md 2>/dev/null || echo "No README.md found"
CLAUDE.md:
!cat CLAUDE.md 2>/dev/null || echo "No CLAUDE.md found"
MCP servers configured (registries: project .mcp.json; ~/.claude.json project + user scope — Claude Code does not register MCP servers in settings.json):
!python3 -c "import json; s=json.load(open('.mcp.json')).get('mcpServers',{}); print('project (.mcp.json):', list(s.keys()) if s else 'none')" 2>/dev/null; python3 -c "import json,os; d=json.load(open(os.path.expanduser('~/.claude.json'))); loc=d.get('projects',{}).get(os.getcwd(),{}).get('mcpServers',{}); usr=d.get('mcpServers',{}); print('project (~/.claude.json):', list(loc.keys()) if loc else 'none'); print('user:', list(usr.keys()) if usr else 'none')" 2>/dev/null || echo "none found"
Scripts directory:
!ls scripts/ 2>/dev/null | head -10 || echo "no scripts/ directory"
Recent git activity:
!git log --oneline -8 2>/dev/null || echo "no git history"
Source files (sampled):
!find . -maxdepth 3 \( -name "*.ts" -o -name "*.tsx" -o -name "*.js" -o -name "*.py" -o -name "*.go" -o -name "*.rs" \) 2>/dev/null | grep -v node_modules | grep -v ".git" | head -20
Active topic (derived from first word of $ARGUMENTS if it matches a known topic keyword):
!FIRST=$(echo "$ARGUMENTS" | awk '{print tolower($1)}'); if [ -n "$FIRST" ] && { [ -f "$HOME/.claude/ramp/schemas/$FIRST.md" ] || [ -f ".claude/knowledge-graphs/schemas/$FIRST.md" ]; }; then echo "$FIRST"; else echo "claude-code"; fi
Detected signals (topic-scoped) (schema-declared probes for the active topic):
!FIRST=$(echo "$ARGUMENTS" | awk '{print tolower($1)}'); if [ -n "$FIRST" ] && { [ -f "$HOME/.claude/ramp/schemas/$FIRST.md" ] || [ -f ".claude/knowledge-graphs/schemas/$FIRST.md" ]; }; then TOPIC="$FIRST"; else TOPIC="claude-code"; fi; python3 "$CLAUDE_PLUGIN_ROOT/ramp_core.py" detect "$TOPIC" 2>/dev/null || echo "DETECT_UNAVAILABLE"
Topic schema (project/global schemas, then the plugin's bundled topics/ — composite if sources: declared):
!FIRST=$(echo "$ARGUMENTS" | awk '{print tolower($1)}'); if [ -n "$FIRST" ] && { [ -f "$HOME/.claude/ramp/schemas/$FIRST.md" ] || [ -f ".claude/knowledge-graphs/schemas/$FIRST.md" ]; }; then TOPIC="$FIRST"; else TOPIC="claude-code"; fi; SCHEMA=$(cat .claude/knowledge-graphs/schemas/$TOPIC.md 2>/dev/null || cat ~/.claude/ramp/schemas/$TOPIC.md 2>/dev/null || cat "$CLAUDE_PLUGIN_ROOT/topics/$TOPIC.md" 2>/dev/null || echo "SCHEMA_NOT_FOUND: Create a schema at .claude/knowledge-graphs/schemas/$TOPIC.md (project-local) or ~/.claude/ramp/schemas/$TOPIC.md (global)"); echo "$SCHEMA"; if echo "$SCHEMA" | grep -q "^sources:"; then for SRC in $(echo "$SCHEMA" | grep "^sources:" | head -1 | sed 's/sources: *//' | tr -d '[]' | tr ',' '\n' | tr -d ' '); do [ -n "$SRC" ] && { echo ""; echo "---"; echo "# Sourced schema: $SRC"; cat ".claude/knowledge-graphs/schemas/$SRC.md" 2>/dev/null || cat "$HOME/.claude/ramp/schemas/$SRC.md" 2>/dev/null || cat "$CLAUDE_PLUGIN_ROOT/topics/$SRC.md" 2>/dev/null || echo "SCHEMA_NOT_FOUND: $SRC"; }; done; fi
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 First seen · 690 lines · 0 tokens per session scan C 884f51f9dbf6
up is a command published in the GitHub repository gf-labs/ramp (2 stars, last pushed 1mo ago), licensed MIT. It adds 28 tokens to every session and 12,407 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it C with 2 findings (strips warnings and disclaimers, reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
review
Cold re-quiz on code that already shipped — your own session commits, not the change in front of you.
start-1-8
Start Lesson 1.8 - Power Features.
cheatsheet
Generate a one-page exam cheatsheet from course-index and errors/log.md. Outputs to cheatsheet/final.md. Optionally convert to PDF.
learn-story-flow
Learn story-flow concepts with interactive guidance for junior developers.
no-vibe
Enter no-vibe mode in OpenCode (tutor mode, no direct project file writes).
teach-me-testing
Teach testing progressively through structured sessions. Use when user says ""lets learn testing"" or ""I want to study test practices"".