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 tomzx/agents --skill refactor-implementationgit clone --depth 1 https://github.com/tomzx/agentsWrote 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/tomzx/agents/refactor-implementation)<a href="https://agentmods.dev/skills/tomzx/agents/refactor-implementation"><img src="https://agentmods.dev/badge/skills/tomzx/agents/refactor-implementation/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/tomzx/agents/refactor-implementation"><img src="https://agentmods.dev/badge/skills/tomzx/agents/refactor-implementation.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 | $0.00121 | $0.02803 |
| Opus 5.5 | $0.00048 | $0.01121 |
| Sonnet 5.5 | $0.00024 | $0.00561 |
| Haiku 4.5 | $0.00012 | $0.00280 |
Grade A, and why
refactor-implementation scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 22d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 190 lines — stays where its author put it; the contents beside it link to each section on GitHub.
TODAY=!date +%Y-%m-%d
Refactor Implementation
Refactors the change just produced by create-implementation, adding only the abstractions and seams it needs to stay small, cohesive, and testable, and deliberately leaving everything else alone.
It applies the behavior-preservation and dependency-breaking techniques from Michael Feathers' Working Effectively with Legacy Code to new code. The goal is not to fix untested legacy code, but to stop fresh code from turning into it. The guiding constraint is minimum abstraction: every seam and every extracted type must justify its place, or it is bloat.
Prerequisites
- Apply the shared SDLC conventions in
skills/sdlc/references/shared.md. - If no argument is provided, locate the feature directory under
.sdlc/features/whose frontmatterissuefield references$ISSUE_NUMBER. - Implementation is complete on the current branch and its tests currently pass (
/create-implementationran first). - The implementation diff is available (
git diff <base>...HEAD, or the files and lines named in context or$1). - Tests exist for the behavior being restructured; if the touched code is under-tested, characterization tests are written as part of this skill.
- Optional:
.sdlc/features/N-<slug>/specification.md,tests.md, and anyreview-implementation.mdfindings, for context on what the change must preserve.
How This Relates to Others
| Skill | Relationship |
|---|---|
create-implementation |
Produces the change this skill refactors. It must have run first and left the tests green. |
review-implementation |
Reviews the refactored result. This skill runs before it and hands off to it. |
analyze-test-coverage |
Its uncovered-code table often shows exactly where a seam is missing or a characterization test belongs. |
propagate-changes |
Run after refactoring if the structure change makes a specification, plan, or documentation stale. |
The Minimum Abstraction Rule
Introduce an abstraction or a seam only when at least one justification holds. If none holds, leave the code alone.
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.
- 22d ago Changed · -3 lines d78a194940bd
- 25d ago Changed 867138075b84
- 1mo ago First seen · 193 lines · 121 tokens per session scan A 4ec21f646c8e
refactor-implementation is a skill published in the GitHub repository tomzx/agents (13 stars, last pushed yesterday), licensed MIT. It adds 121 tokens to every session and 2,803 once invoked, about $0.0005 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 2026-09-29.
Other skills, from other repositories
adk-go-self-review
Review an ADK Go change the way a maintainer will — a fresh-context pass over the whole diff, five lenses (correctness and tests, scope, simplicity, style, adk-python parity), and the mutation check that proves your tests pin the change. Use before opening a PR, before any later push that changes code, and when asked…
adversarial-reviewer
Stress-test a code change for concrete correctness defects, unsafe assumptions, and failure modes. Use when the user explicitly asks for an adversarial review, a deep bug hunt, or to tear a change apart, or to check your own change before submitting it. Do not use for ordinary review, style feedback, or general…
go-testing
Trigger: Go tests, go test coverage, Bubbletea teatest, golden files. Apply focused Go testing patterns.
semgrep-rule-variant-creator
Creates language variants of existing Semgrep rules. Use when porting a Semgrep rule to specified target languages. Takes an existing rule and target languages as input, produces independent rule+test directories for each language.
brooks-sweep
Full-sweep mode: runs a unified analysis across all quality dimensions — code decay, architecture, tech debt, and test quality — then applies fixes directly to the codebase. Safe changes are auto-applied; risky changes are confirmed before execution. Drawing on twelve classic engineering books. Triggers when: user…
plugin-review
Review plugin quality with tiered checks and dependency scoping. Use for PR and pre-release audits.