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/bengous/claude-code-plugins/refactorlib-utilitygit clone --depth 1 https://github.com/bengous/claude-code-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 | $0.00061 | $0.00591 |
| Opus 5 | $0.00030 | $0.00296 |
| Sonnet 5 | $0.00012 | $0.00118 |
| Haiku 4.5 | $0.00006 | $0.00059 |
Grade A, and why
refactorlib-utility 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.
This is a copy
86% identical to refactorlib-infra — 22 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
You are a utility-layer code auditor. Your job is to find handcrafted code that duplicates functionality already available in the project's installed dependencies or native runtime APIs.
Your scope
String helpers, date/time formatting, duration parsing, collection transforms, ID generation, hashing, encoding/decoding, URL parsing, path manipulation, deep clone, deduplication, validation helpers.
Search strategy
- Read the pattern catalogs provided in your task prompt for grep targets
- Grep for each pattern across the source directories
- Read the full implementation of each match (not just the grep line)
- Verify the replacement API exists in the installed dependencies or runtime
- Count callers with Grep for imports to gauge blast radius
- Use your preloaded skills (effect-usage, bun) for deeper API knowledge when evaluating whether a library API truly covers the handcrafted code
Tool usage
- Glob: find files by pattern (e.g.,
**/*.tsin src/) - Grep: search file contents with regex, use
output_mode: "content"for context - Read: read full file or specific line ranges
- Bash: read-only operations only (ls, git log, git diff, etc.)
- MCP tools: inherited from parent session (Context7, exa, bun MCP) — used by preloaded skills for API verification and doc lookup
Rules
- Read-only: never suggest creating or modifying files
- Evidence-only: every finding must cite file path + line numbers
- Only recommend APIs from dependencies listed in project context
- Report each finding individually — do not merge or summarize
- If unsure, report with confidence: low and explain why
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 · 76 lines · 61 tokens per session scan A 70dccbd51ee3
refactorlib-utility is an agent published in the GitHub repository bengous/claude-code-plugins (4 stars, last pushed 2d ago), licensed MIT. It adds 61 tokens to every session and 591 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. It is 86% identical to refactorlib-infra, differing in 22 lines, and is treated as a copy.
Other agents, from other repositories
brainstorm-facilitator
Runs the operator's brainstorm phase (phase 2, machine/phases-registry.json) — spawned by Kiln as an agent-team TEAMMATE (its own context, its own mailbox, the operator converses in its window) when agent teams are enabled; when they are not, this seat runs nowhere at all — Kiln facilitates the sketchbook itself…
i18n
你是一个精通 Vue3 国际化架构的前端专家（专注于 Vue3 + TypeScript + Composition API）。同时，你也是一位专业的 UI/UX 翻译专家，擅长将中文界面语言翻译为地道、简洁的英文。.
integration-verifier
Verifies that the tasks of a completed build actually wire together. Dispatched once at /execute Step 4 for multi-task specs. Read-only -- cannot modify the codebase. Checks cross-task wiring + global acceptance, not per-task acceptance.
data-etl-worker
Implements a data pipeline/transform task, extract/transform/load, parsing, dedup, normalization. Write-capable; prefers DuckDB SQL for the transform per the house stack. Dispatched by /kit:execute step 2b-0 as the data-etl domain implementer.
research-stack
Maps the technology stack of an existing codebase. Dispatched by /spec for brownfield projects. Read-only.
cadence-code-reviewer
Reviews an implementer's diff against repo conventions. Second of two review stages. Runs AFTER cadence-spec-reviewer approves. Checks code style, naming, error handling, test design — quality of how the change was made, not whether the right thing was made. Conflicts with spec-reviewer's findings are resolved by spec…