rforge:impact

A command that examines how a change in one R package could affect related packages in the same software ecosystem.

In plain words
What is it for?
Use it to list affected packages, estimate follow-up work, identify changed functions or APIs, set a severity level, and plan mitigation.
Why use it?
It reveals downstream work and breaking changes before a rename or API change causes problems elsewhere.

Command

Install

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.

agentmods
npx agentmods add commands/data-wise/claude-plugins/impact
Clone the repo
git clone --depth 1 https://github.com/Data-Wise/claude-plugins
Per session 11 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 501 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00011 $0.00501
Opus 5 $0.00005 $0.00251
Sonnet 5 $0.00002 $0.00100
Haiku 4.5 $0.00001 $0.00050

Measured yesterday against content hash d061066af462, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

rforge:impact 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.

rforge/commands/impact.md · 95 lines

What it actually says

/rforge:impact - Change Impact Analysis

Analyze the ripple effects of changes across your R package ecosystem.

What It Does

Uses the rforge_impact MCP tool to:

  • Identify affected packages
  • Estimate cascade workload
  • Find breaking changes
  • Calculate update priority
  • Provide mitigation strategies

Usage

# Impact of recent changes
/rforge:impact

# Impact of specific change
/rforge:impact "Rename extract_mediation to extract_med"

# Impact for function change
/rforge:impact --function extract_mediation

Output

Returns impact assessment with:

  • Severity: LOW/MEDIUM/HIGH/CRITICAL
  • Affected Packages: List with details
  • Cascade Workload: Estimated time
  • Breaking Changes: Functions/APIs affected
  • Mitigation: Suggested strategies

Examples

Medium Impact

📊 IMPACT ANALYSIS

Severity: MEDIUM
Affected: 2 packages (probmed, medsim)

probmed:
  • 1 function call to update
  • Tests: 12 tests reference old API
  • Est. work: 2 hours

medsim:
  • 1 vignette example
  • Est. work: 1 hour

Total cascade: 3 hours
Recommended: Update & release in sequence

High Impact (Breaking Change)

⚠️ IMPACT ANALYSIS

Severity: HIGH (Breaking change)
Affected: 3 packages + indirect

Direct Impact:
  • probmed: 5 functions, 47 test cases
  • medsim: 2 examples, 1 vignette
  • sensitivity: 1 function call

Indirect Impact:
  • mediationverse: May need meta-update

Total cascade: 8-12 hours
Recommended: Deprecation path + major version bump

Use When

  • Before making API changes
  • Planning breaking changes
  • Estimating release workload
  • Coordinating ecosystem updates
  • /rforge:deps - See dependency structure
  • /rforge:cascade - Plan coordinated updates
  • /rforge:doc-check - Check documentation impact
Changes

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.

  1. yesterday First seen · 95 lines · 11 tokens per session scan A d061066af462

Subscribe to this mod's changes

rforge:impact 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 501 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.