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/thoroughgit 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 | $0.00019 | $0.01993 |
| Opus 5 | $0.00010 | $0.00996 |
| Sonnet 5 | $0.00004 | $0.00399 |
| Haiku 4.5 | $0.00002 | $0.00199 |
Grade A, and why
rforge:thorough 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.
How it starts
The opening of the file, as written. The whole thing — 290 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/rforge:thorough - Comprehensive R Package Analysis
Deep, comprehensive analysis using background R processes. Takes 2-5 minutes but provides publication-quality insights.
Usage
# Thorough analysis
/rforge:thorough
# With context
/rforge:thorough "Prepare RMediation for CRAN"
# Specific analysis type
/rforge:thorough --type full_check
/rforge:thorough --type coverage
/rforge:thorough --type performance
What It Does
Runs comprehensive R analysis in background:
-
Launch Phase (5 sec)
- Start background R process
- Return task ID immediately
- Show estimated duration
-
Monitoring Phase (2-5 min)
- Poll task every 10 seconds
- Show progress updates
- Display intermediate results
-
Results Phase (5 sec)
- Retrieve complete results
- Synthesize comprehensive report
- Provide detailed recommendations
Output Example
🔬 Launching thorough analysis...
Background R analysis started (task: abc123)
Estimated duration: 3-5 minutes
You can:
- Wait here (I'll show progress)
- Do other work (run /rforge:results abc123 later)
- Cancel anytime (Ctrl+C)
[10s] 📊 Running R CMD check...
[20s] 📊 Still running checks (platform: ubuntu)...
[30s] 📊 Checking examples...
[45s] ✅ R CMD check complete: 0 errors, 0 warnings, 0 notes
[60s] 📊 Running test suite...
[75s] 📊 Calculating coverage...
[90s] ✅ Coverage analysis complete: 94.2%
[120s] 📊 Running performance benchmarks...
[150s] ✅ Performance analysis complete
✅ Thorough analysis complete! (2m 35s)
═══════════════════════════════════════════════════
🎯 COMPREHENSIVE ANALYSIS: RMediation
📦 PACKAGE INFO:
• Version: 2.0.1
• R dependency: >= 3.5.0
• Imports: 3 packages
• Suggests: 5 packages
🔍 R CMD CHECK: ✅ PASS
• Errors: 0
• Warnings: 0
• Notes: 0
• Platforms tested: ubuntu-latest, macos-latest, windows-latest
• Time: 45 seconds
🧪 TEST RESULTS: ✅ EXCELLENT
• Tests: 187/187 passing
• Coverage: 94.2%
• Test files: 12
• Assertions: 1,245
• Performance: 2.3 seconds
📊 COVERAGE BREAKDOWN:
• R/: 96.1% (138/143 lines)
• R/ci_mediation.R: 98.5%
• R/bootstrap.R: 92.3% ⚠️ (needs 2 more tests)
• R/utils.R: 100%
⚡ PERFORMANCE:
• ci_mediation(): 2.3ms (fast)
• bootstrap_ci(): 145ms (acceptable)
• Benchmarked: 1000 iterations
• No regressions detected
🎯 DEPENDENCY IMPACT:
• Reverse dependencies: 5 packages
• All passing with current version
• 2 packages would be affected by API change
📝 DOCUMENTATION:
• Roxygen: ✅ Up to date
• Vignettes: 3 found, all build successfully
• Examples: All run without errors
• NEWS.md: Last entry 2.0.0 (needs update for 2.0.1)
• README badges: All current
🌐 CRAN STATUS:
• Current CRAN version: 2.0.0
• Check results: All OK (last check: 2 days ago)
• Incoming: No submissions pending
• Reverse check results: All passing
💯 OVERALL HEALTH SCORE: 95/100 (A)
Grade breakdown:
• Code quality: 96/100 (excellent test coverage)
• Documentation: 92/100 (minor NEWS update needed)
• CRAN compliance: 100/100 (perfect)
• Performance: 94/100 (good)
• Maintenance: 91/100 (active development)
═══════════════════════════════════════════════════
📋 DETAILED RECOMMENDATIONS:
🔥 BEFORE RELEASE:
1. Update NEWS.md with 2.0.1 changes
2. Add 2 tests to R/bootstrap.R (coverage < 95%)
3. Update version badge in README
4. Run final check: R CMD check --as-cran
🎯 FOR THIS CHANGE:
1. Implement bootstrap algorithm update (3 hours)
2. Update algorithm vignette
3. Benchmark new vs old performance
4. Update 2 affected packages (mediate, sensitivity)
⭐ OPTIONAL IMPROVEMENTS:
1. Add performance benchmarks to vignettes
2. Create pkgdown site
3. Add code coverage badge
═══════════════════════════════════════════════════
Next steps:
[1] Generate release checklist
[2] Create cascade plan for dependents
[3] Export report to markdown
[4] Something else
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 · 290 lines · 19 tokens per session scan A a6c9452313de
rforge:thorough is a command published in the GitHub repository Data-Wise/claude-plugins (7 stars, last pushed 5d ago), licensed MIT. It adds 19 tokens to every session and 1,993 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
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.