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/nextgit 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 | $0.00011 | $0.00681 |
| Opus 5 | $0.00005 | $0.00341 |
| Sonnet 5 | $0.00002 | $0.00136 |
| Haiku 4.5 | $0.00001 | $0.00068 |
Grade A, and why
rforge:next 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 — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/rforge:next - Smart Task Recommendation
Get intelligent recommendations for what to work on next based on ecosystem context.
What It Does
Uses the rforge_next MCP tool to:
- Analyze all .STATUS files
- Consider dependencies
- Evaluate blocking issues
- Prioritize by impact
- Suggest optimal next task
Usage
# Get next task
/rforge:next
# Next task for specific package
/rforge:next medfit
# Next task with context
/rforge:next --context "Before release"
Output
Returns task recommendation with:
- Task Details: What to work on
- Rationale: Why this task now
- Impact: What it unblocks
- Estimated Time: How long it will take
- Context: Related tasks/blockers
Examples
High Priority Task
📋 NEXT TASK RECOMMENDATION
Task: Fix bug #234 - segfault in extract_mediation
ID: T-2025-01-15-002
Package: medfit
Priority: HIGH
Why now:
• Blocking probmed release
• Affects 2 packages
• CRAN submission waiting
• High user impact
Estimated time: 2-3 hours
Context:
• 3 GitHub issues reference this
• Already has test case
• Fix will unblock 2 downstream releases
Recommendation: Work on this immediately
Strategic Task
📋 NEXT TASK RECOMMENDATION
Task: Add bootstrap confidence intervals
ID: T-2025-01-15-001
Package: medfit
Priority: MEDIUM
Why now:
• No urgent blockers
• Good time for feature work
• Complements recent changes
• Low ecosystem impact
Estimated time: 4-6 hours
Context:
• Requested by 3 users
• Aligns with v2.2.0 roadmap
• Can be done without cascade
Alternative tasks:
• Update documentation (1 hour, quick win)
• Research weighted mediation (exploratory)
Before Release
📋 NEXT TASK RECOMMENDATION
Context: Before Release
Task: Complete documentation updates
ID: DOC-SWEEP
Priority: HIGH (release blocker)
Checklist:
✓ NEWS.md updated
✗ README examples (2 outdated)
✗ Vignette cross-refs (3 packages)
✗ API documentation (1 function)
Estimated time: 1.5 hours
Why now:
• Release planned for next week
• All code changes complete
• CRAN requires current docs
• Quick wins available
Recommendation: Focus on docs before release
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 · 136 lines · 11 tokens per session scan A 261925c02653
rforge:next is a command published in the GitHub repository Data-Wise/claude-plugins (7 stars, last pushed 5d ago), licensed MIT. It adds 11 tokens to every session and 681 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.