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/rubencodeforges/codeforges-claude-plugin/map-class-usagegit clone --depth 1 https://github.com/rubenCodeforges/codeforges-claude-pluginWhat 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 | $0.00020 | $0.00337 |
| Opus 5 | $0.00010 | $0.00169 |
| Sonnet 5 | $0.00004 | $0.00067 |
| Haiku 4.5 | $0.00002 | $0.00034 |
Grade A, and why
map-class-usage 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.
What it actually says
Invoke the @usage-finder sub-agent to build a comprehensive usage map for the specified class.
The usage map should include:
-
Class Analysis:
- Extract all public methods with their signatures
- Extract all public fields/properties with their types
- Identify constructors and static members
- Note any inherited classes or interfaces
-
Usage Search:
- Find all usages of each method across the codebase
- Find all usages of each field/property
- Categorize usages by type (method calls, field access, inheritance, etc.)
- Include file paths and line numbers for each usage
-
Structured Output:
- Generate JSON format for programmatic consumption
- Include usage counts and location summaries
- Provide actionable insights (dead code, high coupling, refactoring opportunities)
-
Analysis Summary:
- Most used methods/fields
- Unused members (dead code candidates)
- Breaking change impact assessment
- Refactoring recommendations
Usage: /map-class-usage <ClassName> or /map-class-usage <path/to/ClassFile>
Examples:
/map-class-usage UserService/map-class-usage src/services/PaymentProcessor.java/map-class-usage DatabaseManager --exclude-tests
The agent will search for the class, analyze its structure, find all usages, and present results in both JSON (for machines) and Markdown table (for humans) formats.
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 · 41 lines · 20 tokens per session scan A d00a0233bb99
map-class-usage is a command published in the GitHub repository rubenCodeforges/codeforges-claude-plugin (2 stars, last pushed 9mo ago), licensed MIT. It adds 20 tokens to every session and 337 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
update-changelog
Update CHANGELOG.md with new entry based on git diff.
ask
Ask questions about memories and get context-aware answers.
recent
Show recent memories and activity timeline.
search
Search memories for specific content or patterns.
stats
Show memory statistics and storage information.
pm-diagnose
Start a bearing fault diagnosis workflow on a vibration signal.