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 kulmam92/cc-best-practices-marketplace --skill bp-refactorgit clone --depth 1 https://github.com/kulmam92/cc-best-practices-marketplaceWrote 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/kulmam92/cc-best-practices-marketplace/bp-refactor)<a href="https://agentmods.dev/skills/kulmam92/cc-best-practices-marketplace/bp-refactor"><img src="https://agentmods.dev/badge/skills/kulmam92/cc-best-practices-marketplace/bp-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/kulmam92/cc-best-practices-marketplace/bp-refactor"><img src="https://agentmods.dev/badge/skills/kulmam92/cc-best-practices-marketplace/bp-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 | $0.00049 | $0.00426 |
| Opus 5 | $0.00024 | $0.00213 |
| Sonnet 5 | $0.00010 | $0.00085 |
| Haiku 4.5 | $0.00005 | $0.00043 |
Grade A, and why
bp-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 11d 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.
What it actually says
Safe Refactoring Protocol
Never refactor without locking down existing behavior first. This follows Boris Cherny's 4-step legacy refactoring protocol.
Steps
-
Write characterization tests FIRST -- Before touching any logic, write tests that lock down the current behavior. Even if the current behavior is buggy, test it as-is. For large refactors (50k+ LOC), Boris recommends spending the first 4 days purely on characterization tests.
-
Check CLAUDE.md for load-bearing walls -- Verify that the area to be refactored is not protected. If it is, stop and discuss with the developer.
-
Plan atomic chunks -- Split the refactor into independently landable pieces:
- Interfaces and types first
- Helper functions second
- Implementation changes last
- Each chunk should be independently reviewable and revertable
-
Execute one chunk at a time -- Implement each chunk and run
/bp-verifyafter each one. Never combine multiple chunks into a single change. -
If a chunk fails -- Revert the chunk entirely and rescope. Do NOT patch on top of a failed refactoring step. Go back to the plan and try a different approach.
Anti-Patterns
- DO NOT refactor and change behavior simultaneously -- separate them
- DO NOT skip characterization tests -- they are the safety net
- DO NOT submit one giant diff -- break it into atomic, landable chunks
- DO NOT patch around failures -- revert and rescope
Quality Checks
- Characterization tests pass before AND after each chunk
- No chunk exceeds 200 lines of changes
- Existing behavior is preserved (unless intentionally changed in a separate PR)
- Load-bearing walls are respected
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.
- 11d ago First seen · 40 lines · 49 tokens per session scan A 61c915e58346
bp-refactor is a skill published in the GitHub repository kulmam92/cc-best-practices-marketplace (2 stars, last pushed 5mo ago), licensed MIT. It adds 49 tokens to every session and 426 once invoked, about $0.0002 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
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
tika-eval-compare
Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".
neuron-evaluation-engineer
Create and run AI evaluations with datasets, assertions, and output drivers in Neuron AI. Use this skill whenever the user mentions evaluation, testing AI systems, creating evaluators, dataset-driven testing, assertion-based validation, or wants to measure AI system performance. Also trigger for tasks involving…
jetson-validate-image
Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.
atmos-validation
Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.
skill-benchmark
Benchmark AI skill effectiveness by measuring implementation quality against legacy constraints.