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/data-wise/claude-plugins/analyzegit clone --depth 1 https://github.com/Data-Wise/claude-pluginsWhat 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 | $0.00015 | $0.02464 |
| Opus 5 | $0.00008 | $0.01232 |
| Sonnet 5 | $0.00003 | $0.00493 |
| Haiku 4.5 | $0.00002 | $0.00246 |
Grade A, and why
rforge:analyze 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 — 394 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/rforge:analyze - Mode-Aware R Package Analysis
Analyze R package ecosystem with explicit control over analysis depth and performance.
Mode System
Current Mode: {{mode | default: "default"}}
Mode Selection
Parse the user's request to detect mode:
- If user explicitly provides "debug", "optimize", or "release" → use that mode
- Otherwise → use "default" mode (fast, balanced)
Default Mode (< 10 seconds)
Purpose: Daily check-ins, quick status validation
Behavior:
- Focus on critical issues only
- Recent changes (last 7 days)
- High-priority dependencies
- Quick health metrics
- Balanced, actionable output
Tools: rforge_detect, rforge_status, rforge_quick_health
Time Budget: MUST complete in < 10 seconds
Output:
- Critical issues highlighted
- Health score
- Next recommended action
- Quick summary
Debug Mode (30s - 2 minutes)
Purpose: Finding bugs, investigating issues, troubleshooting
Behavior:
- Deep inspection of all components
- All dependencies (recursive analysis)
- Complete file scans (R/, tests/, vignettes/)
- Detailed error traces with stack traces
- Hidden configuration checks
- Cache validation
- Environment inspection
Tools: All RForge MCP tools with detailed flags
Time Budget: SHOULD complete in < 2 minutes
Output:
- Detailed error traces
- Complete dependency tree
- Per-file analysis
- Hidden issues revealed
- Root cause identification
Optimize Mode (1-3 minutes)
Purpose: Speed improvements, performance tuning, bottleneck detection
Behavior:
- Profile R code execution
- Package load time analysis
- Dependency bloat detection
- Function call hotspots
- Memory usage patterns
- Benchmark comparisons
- Test execution time analysis
Tools: rforge_profile, performance benchmarks, load time analysis
Time Budget: SHOULD complete in < 3 minutes
Output:
- Top 3-5 bottlenecks identified
- Concrete optimization suggestions
- Quantified performance impact
- Before/after projections
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.
- 2d ago First seen · 394 lines · 15 tokens per session scan A cf182e7b9921
rforge:analyze is a command published in the GitHub repository Data-Wise/claude-plugins (7 stars, last pushed 6d ago), licensed MIT. It adds 15 tokens to every session and 2,464 once invoked, about $0.0001 per session on Opus 5. 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 commands, from other repositories
OPSX: Continue
Continue working on a change - create the next artifact (Experimental).
OPSX: Fast Forward
Create a change and generate all artifacts needed for implementation in one go.
analyze
Perform a full 3-stage analysis of a source following the Reality Check methodology.
synthesize
Create a cross-source synthesis across multiple source analyses and claims.
extract
Quick claim extraction from a source without full 3-stage analysis.
validate
Check database integrity and referential consistency.