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 skills/cosmix/loom/loom-refactoringnpx skills add cosmix/loom --skill loom-refactoringgit clone --depth 1 https://github.com/cosmix/loomWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/cosmix/loom/loom-refactoring)<a href="https://agentmods.dev/skills/cosmix/loom/loom-refactoring"><img src="https://agentmods.dev/badge/skills/cosmix/loom/loom-refactoring.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00022 | $0.02022 |
| Opus 5 | $0.00011 | $0.01011 |
| Sonnet 5 | $0.00004 | $0.00404 |
| Haiku 4.5 | $0.00002 | $0.00202 |
Grade A, and why
loom-refactoring 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 — 163 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Refactoring
Overview
Change the internal structure of code without changing its observable behavior. Restructuring and behavior change are two different activities — never do both in one commit.
The cardinal rule
Behavior-preserving, tests green before AND after. If you can't prove behavior is unchanged, you're not refactoring — you're rewriting, and you need different discipline (characterization tests, feature flags; see /loom-code-migration).
Corollaries an expert never violates:
- Tests are the safety net. Run them before you touch anything (establish green). If there are none for the code you're changing, write characterization tests first (below) — do not refactor untested legacy blind.
- Tiny reversible steps. One mechanical move at a time; re-run tests after each. When something breaks, inspect the small current diff and use the repository's approved recovery workflow rather than discarding unrelated work.
- Separate refactor commits from behavior-change commits. A
refactor:commit must be a no-op at runtime — reviewers can trust the diff without re-verifying logic. Mixing a bug fix into a rename hides the fix and poisonsgit bisect. (Commit mechanics:/loom-git-workflow.) - Don't change tests and production code in the same step. If a refactor "requires" editing a test's assertions, behavior changed — stop and reconsider.
Not this skill
- Fixing a bug →
/loom-debugging(that is a behavior change; write the failing test first). - Adding a feature → implement it, then refactor separately.
- Migrating framework/API/schema →
/loom-code-migration(behavior does move; needs parallel-run/rollback).
Name the smell, then apply the matching move
Refactoring is not "make it nicer" — identify a specific smell and apply its canonical move. If you can't name the smell, don't refactor.
| Smell | Signal | Move |
|---|---|---|
| Long method (>50 LOC) | Scrolling to read one function; comment-delimited sections | Extract Method; Decompose Conditional |
| Large class (>300 LOC) | Many unrelated fields/methods; low cohesion | Extract Class; Move Method |
| Duplicated logic | Same block in 2+ places (will drift) | Extract Method/Function, then hoist to shared location |
| Feature envy | Method uses another object's data more than its own | Move Method to the class that owns the data |
| Primitive obsession | Bare strings/ints for domain concepts; validation scattered | Introduce Value Object / newtype |
| Data clumps | Same 3-4 params travel together everywhere | Introduce Parameter Object |
| Shotgun surgery | One conceptual change forces edits in many files | Consolidate the responsibility into one module |
| Divergent change | One module changed for many unrelated reasons | Split by axis of change (SRP) |
| Deep nesting (>3) | Arrow-shaped code | Guard clauses; Extract Method |
| Type-code switch | switch/match on a type tag, repeated |
Replace Conditional with Polymorphism |
| Magic number/string | Unexplained literal | Named constant |
| Speculative generality | Abstraction/param with one caller "for later" | Inline it — YAGNI |
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 Changed · -35 tokens per session 6ec7fdce5527
- 6d ago First seen · 163 lines · 57 tokens per session scan A ce5a483ef1c3
loom-refactoring is a skill published in the GitHub repository cosmix/loom (54 stars, last pushed yesterday), licensed MIT. It adds 22 tokens to every session and 2,022 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 2026-08-30.
Other skills, from other repositories
workers-best-practices
Reviews and authors Cloudflare Workers code against production best practices. Load when writing new Workers, reviewing Worker code, configuring wrangler.jsonc, or checking for common Workers anti-patterns (streaming, floating promises, global state, secrets, bindings, observability). Biases towards retrieval from…
find-journalists
Build, refine, dedupe, and enrich small fit-checked journalist lists for newsjack campaigns. Uses the newsjack CLI (preferred) or the medialyst MCP for news search and journalist enrichment, and falls back to a best-effort local mode with no verified contacts; the agent owns how returned data is organized.
story-origin-check
Recover the first public timestamp and canonical major coverage for a newsjacking signal, then decide whether newer coverage is the same story, a different story, or a materially new development.
annotating-task-lineage
Annotate Airflow tasks with data lineage using inlets and outlets. Use when the user wants to add lineage metadata to tasks, specify input/output datasets, or enable lineage tracking for operators without built-in OpenLineage extraction.
ai-visibility-writing
Audit, question, suggest, or fact-preservingly revise a press release, blog post, contributed article, or expert explainer so AI answer systems can more easily retrieve, understand, quote, and cite its useful information. Use when someone asks for AI visibility, AI search, answer-engine, AEO, GEO, AI Overview, or…
aws-cloudformation-cloudfront
Provides AWS CloudFormation patterns for CloudFront distributions, origins (ALB, S3, Lambda@Edge, VPC Origins), CacheBehaviors, Functions, SecurityHeaders, parameters, Outputs and cross-stack references. Use when creating CloudFront distributions with CloudFormation, configuring multiple origins, implementing caching…