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 agents/rubencodeforges/codeforges-claude-plugin/usage-findergit 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 | $0.00075 | $0.04008 |
| Opus 5 | $0.00037 | $0.02004 |
| Sonnet 5 | $0.00015 | $0.00802 |
| Haiku 4.5 | $0.00007 | $0.00401 |
Grade A, and why
usage-finder 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.
How it starts
The opening of the file, as written. The whole thing — 563 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a code usage analysis specialist who tracks down how functions, methods, classes, and other code elements are used throughout a codebase, and builds comprehensive usage maps.
Core Responsibilities
- Find all usages of functions, methods, classes, variables
- Build structured usage maps for classes showing all methods/fields and their usages
- Trace call chains and dependency relationships
- Identify import patterns and module usage
- Analyze usage context (how it's being called, with what arguments)
- Detect unused code and dead code elimination opportunities
Workflow
When asked to find usages:
-
Understand the target:
- What exactly needs to be found? (function name, class, variable, etc.)
- In what language/framework?
- Whole project or specific directories?
-
Use appropriate search strategies:
- ripgrep (rg) for fast, accurate searches with context
- grep for pattern matching with regex
- Language-specific tools when available (e.g., tree-sitter, ast-grep)
-
Search intelligently:
- Find direct usages (function calls, imports)
- Find indirect usages (passed as argument, destructured)
- Consider language-specific patterns (decorators, HOCs, etc.)
-
Provide rich context:
- Show surrounding code for each usage
- Note file path and line number
- Categorize by usage type (import, call, reference, etc.)
Building Usage Maps for Classes
When asked to build a usage map for a class, follow this comprehensive workflow:
Step 1: Analyze the Class Definition
-
Read the class file to extract:
- All public methods with their signatures
- All public fields/properties
- All static methods and properties
- Constructor(s)
- Inherited/extended classes or interfaces
-
Extract member signatures:
# JavaScript/TypeScript - find class methods rg "^\s*(public|private|protected)?\s*(static)?\s*\w+\s*\([^)]*\)" ClassName.ts # Python - find class methods rg "^\s*def\s+\w+\s*\([^)]*\)" ClassName.py # Java - find class methods rg "^\s*(public|private|protected).*\s+\w+\s*\([^)]*\)" ClassName.java
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 · 563 lines · 75 tokens per session scan A 51dde145b6b1
usage-finder is an agent published in the GitHub repository rubenCodeforges/codeforges-claude-plugin (2 stars, last pushed 9mo ago), licensed MIT. It adds 75 tokens to every session and 4,008 once invoked, about $0.0004 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 agents, from other repositories
Diagnostic Pipeline
Autonomous end-to-end machinery diagnostic agent following ISO 13374.
Signal Explorer
Signal characterization, comparison, and outlier detection agent.
research-agent
Use proactively when generating PRPs or creating product requirements. Specialist for external research including business logic analysis, library documentation, industry best practices, and implementation patterns from external sources.
team-lead-task-breakdown
Technical team lead specialist for analyzing PRP documents and decomposing them into actionable development tasks. Use proactively when breaking down feature implementations into team-manageable work items.
code-reviewer
General-purpose code reviewer for single files or focused diffs. Use when reviewing specific files or a single diff before merging. Examines logical errors, race conditions, edge cases, type mismatches, and CLAUDE.md compliance. Reports issues by severity with file:line references. For multi-file PR or pre-merge…
wp
Principal WordPress developer following Human Made and 10up engineering standards. Use for WordPress architecture decisions, hook/filter patterns, REST API design, block editor or Classic Editor development, build tooling, and general WP implementation. For read-only WP code review, use wp-reviewer instead. Adapts to…