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 skills add didacrios/ai-coding-protocols --skill refactorgit clone --depth 1 https://github.com/didacrios/ai-coding-protocolsWrote 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/didacrios/ai-coding-protocols/refactor)<a href="https://agentmods.dev/skills/didacrios/ai-coding-protocols/refactor"><img src="https://agentmods.dev/badge/skills/didacrios/ai-coding-protocols/refactor/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/didacrios/ai-coding-protocols/refactor"><img src="https://agentmods.dev/badge/skills/didacrios/ai-coding-protocols/refactor.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00065 | $0.00858 |
| Opus 5.5 | $0.00026 | $0.00343 |
| Sonnet 5.5 | $0.00013 | $0.00172 |
| Haiku 4.5 | $0.00006 | $0.00086 |
Grade A, and why
refactor 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 20d 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 — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Surgical Refactoring Protocol
A protocol for safely improving code quality without changing external behavior. Combines recursive tracing with incremental, test-verified transformations.
When to Activate
- Cleaning up code after a feature is complete
- Reducing method length or cyclomatic complexity
- Aligning existing code with stack standards
- Extracting reusable logic from large methods
- Renaming symbols to match domain language
Core Concepts
- Behavior preservation — refactoring must not change external behavior
- Test shield — green tests must exist before any refactoring begins
- One method at a time — incremental changes, verified after each step
- The "Clean 20" rule — methods over 20 lines are mandatory extraction targets
Detailed Guidance
Pre-Refactor Analysis
Before any modification, perform a recursive check:
- Contracts: Identify all interfaces or types the current code implements by peeking into project files.
- Consumers: Trace all methods that depend on this code to prevent breaking changes.
- Test Shield: Verify that a green test suite exists. If missing, the first "Baby Step" must be creating a test.
Refactoring Targets (The "Clean 20" Rule)
Systematically apply these transformations:
- Method Extraction: If a method > 20 lines, extract logical sub-tasks into private helpers (10-20 lines).
- Complexity Flattening: Replace nested logic with early returns or collection pipelines (map/filter).
- Naming Alignment: Rename symbols to match the domain language found in the relevant stack skill.
- Type Strengthening: Replace
mixed,any, or loose types with strict types or Value Objects.
Execution Protocol
- The "Shadow" Step: Propose the new architecture in a
<thought>block. Explain how it aligns with the tracing rules inrecursive-exploration. - Incremental Apply: Refactor only ONE method at a time.
- Verify: Run tests after every single extraction to ensure the behavioral contract is intact.
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.
- 20d ago Changed · +44 tokens per session ce3f1ac28326
- 2mo ago First seen · 78 lines · 21 tokens per session scan A ab61c4666f3e
refactor is a skill published in the GitHub repository didacrios/ai-coding-protocols (2 stars, last pushed 5d ago), licensed MIT. It adds 65 tokens to every session and 858 once invoked, about $0.0003 per session on Opus 5.5. 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
autoreview
Structured code review through the shared OpenClaw agent-skills installation.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…
omh-code-review
This is an OMH code-review workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
re0-merge
Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…
explore-unknowns
Guide the user through a quadrant walk that maps the unknowns of a task — open by listing the known knowns, then work through known unknowns, unknown knowns, and unknown unknowns one stage at a time, ending with a complete four-quadrant map in the user's hands. Use when a request is ambiguous or underspecified, the…