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/kreek/consult/refactoringnpx skills add kreek/consult --skill refactoringgit clone --depth 1 https://github.com/kreek/consultWrote 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/kreek/consult/refactoring)<a href="https://agentmods.dev/skills/kreek/consult/refactoring"><img src="https://agentmods.dev/badge/skills/kreek/consult/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 | $0.00019 | $0.01098 |
| Opus 5 | $0.00010 | $0.00549 |
| Sonnet 5 | $0.00004 | $0.00220 |
| Haiku 4.5 | $0.00002 | $0.00110 |
Grade A, and why
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 3d 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 — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Refactoring
Iron Law
GREEN BEFORE THE REFACTOR. GREEN AFTER EACH STEP. NEVER MIX STRUCTURE AND BEHAVIOR IN ONE COMMIT.
When to Use
- Changing structure while preserving behavior: legacy refactors, large renames, extractions, migrations, branch by abstraction, strangler fig, Mikado planning, characterization tests, or big-bang rewrite avoidance.
When NOT to Use
- Behavior-first feature work; use
proof. - Commit grouping or git history surgery after changes already exist;
use
git-workflow.
Core Ideas
- Preserve behavior first; add characterization tests where coverage is missing. Separate structural from behavior changes: every commit is one or the other, never both.
- Name the coupling before changing structure: data shape, side effect, module boundary, ownership, time, transport, persistence, or compatibility.
- Make every step small, reversible, and shippable.
- Validate the target shape before moving large amounts of code.
- For public interfaces, use parallel change: expand, migrate callers, then contract. Ask which callers, data, and releases must keep working before adding shims, dual paths, or migration complexity.
- Delete old paths only when traffic/callers have moved and verification proves it.
- Simplification is refactoring: remove accidental complexity only after naming the behavior preserved and the coupling reduced.
Workflow
- Define the current behavior that must not change. Add or identify tests that catch regressions at the public boundary.
- Name the concern being separated and its current coupling point.
- Pick the smallest safe pattern: rename, extract, move, parallel change, branch by abstraction, or strangler. For broad renames, write a rename map first: separate private symbols, file paths, runtime/public keys, persisted names, docs, and compatibility cleanup.
- Record a preservation Proof Contract: unchanged behavior claim, relevant invariant, public boundary, before/after check, evidence.
- For simplification, remove only complexity that has a named cost: hidden mutable state, unnecessary layer, broad helper, scattered behavior, compatibility shim, dead flag, or duplicated rule with divergent meaning.
- Make one structural step, run focused tests, commit. Track any old path left behind with owner and removal condition.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 3d ago First seen · 100 lines · 19 tokens per session scan A e810cdadbc1b
refactoring is a skill published in the GitHub repository kreek/consult (1 stars, last pushed 8d ago), licensed MIT. It adds 19 tokens to every session and 1,098 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 skills, from other repositories
watch
File sentinel that monitors the working directory for changes and marker comments, then auto-triggers appropriate skills. Poll-based via git diff against the last scan commit. Writes intake items for batch processing and routes marker actions through /do. Use for automatic reactions to file changes; do NOT use for…
pr-watch
Local PR watcher. Monitors CI status, automatically fixes failing checks by reading failure logs and applying targeted fixes, then optionally merges when all checks pass. Local CLI analog to Claude Code's cloud auto-fix feature.
qa
Browser-based QA verification. Launches a real browser, navigates the app, clicks buttons, fills forms, and tests user flows. Works as a standalone skill or as a phase end condition in campaigns. Requires Playwright (optional dependency, graceful skip if not installed).
live-preview
Mid-build visual verification loop. Takes screenshots of components during construction, not just after. Catches visual regressions and invisible features before they compound. Requires Playwright or similar screenshot tool.
systematic-debugging
4-phase root cause analysis: observe, hypothesize, verify, fix. Enforces investigation before any code changes. Emergency stop after 2 failed fixes. Prevents shotgun debugging and fix cascades.
claude-code-session-broker
Use when running Arcgentic V2 in Claude Code and fixed Planner, Developer, and Auditor role sessions must be coordinated through a broker.