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/capturegit 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 | $0.00579 |
| Opus 5 | $0.00010 | $0.00290 |
| Sonnet 5 | $0.00004 | $0.00116 |
| Haiku 4.5 | $0.00002 | $0.00058 |
Grade A, and why
rforge:capture 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 — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/rforge:capture - Quick Task Capture
Quickly capture ideas, tasks, and TODOs with automatic context detection.
What It Does
Uses the rforge_capture MCP tool to:
- Capture tasks to .STATUS file
- Auto-detect context (which package)
- Add metadata (timestamp, status)
- Trigger doc cascade detection
- Organize by priority
Usage
# Capture a task
/rforge:capture "Add bootstrap confidence intervals"
# Capture with priority
/rforge:capture "Fix bug #234" --priority high
# Capture idea
/rforge:capture "Research weighted mediation"
Output
Returns confirmation with:
- Task ID: Unique identifier
- Location: Which .STATUS file
- Context: Detected package/project
- Priority: Auto-assigned or manual
- Next Steps: Suggested actions
Examples
Simple Capture
✅ CAPTURED
Task: Add bootstrap confidence intervals
ID: T-2025-01-15-001
Location: medfit/.STATUS
Priority: MEDIUM (auto-detected from keywords)
Context: Feature addition
Added to: medfit/.STATUS (line 42)
Estimated work: 4-6 hours
High Priority Capture
⚠️ CAPTURED (HIGH PRIORITY)
Task: Fix bug #234 - segfault in extract_mediation
ID: T-2025-01-15-002
Location: medfit/.STATUS
Priority: HIGH (manual override)
Context: Bug fix
Related:
• GitHub issue #234
• Affects: probmed, medsim
• Impact: MEDIUM (2 packages)
Recommended: Fix immediately (blocking release)
Idea Capture
💡 CAPTURED (IDEA)
Idea: Research weighted mediation methods
ID: I-2025-01-15-003
Location: research-ideas/.STATUS
Priority: LOW (research/exploration)
Context: New feature exploration
Notes:
• Not blocking anything
• Consider for v3.0.0
• Estimated research: 1-2 weeks
Use When
- During development (quick capture)
- In meetings (capture action items)
- Reading papers (capture ideas)
- Code review (capture TODOs)
Related Commands
/rforge:next- Get next task to work on/rforge:complete- Mark tasks complete/rforge:status- See all captured tasks
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 · 104 lines · 19 tokens per session scan A 9f7ad2a792f7
rforge:capture 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 579 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.