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/ezbuilder/code-brain/safe-refactornpx skills add ezBuilder/code-brain --skill safe-refactorgit clone --depth 1 https://github.com/ezBuilder/code-brainWhat 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 | $0.00020 | $0.00363 |
| Opus 5 | $0.00010 | $0.00181 |
| Sonnet 5 | $0.00004 | $0.00073 |
| Haiku 4.5 | $0.00002 | $0.00036 |
Grade A, and why
safe-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 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.
What it actually says
리팩터링 절차:
- 리팩터링 목표와 비목표를 명시한다.
- 변경 전 검증 명령을 확인한다.
- behavior-lock: 편집 전에 동작을 고정하는 회귀 테스트가 GREEN인지 먼저 확인한다. 커버리지가 없으면 최소 회귀 테스트를 먼저 추가하고, GREEN 베이스라인을 만들 수 없으면 중단·보고한다.
- public behavior가 바뀌지 않도록 범위를 제한한다.
- 삭제, 표준/플랫폼 기능, 이미 설치된 의존성, 한 줄 축약을 먼저 찾는다.
- 가장 안전한 변경부터 위험한 순으로 진행한다.
- 변경 후 동일 검증을 실행해 baseline과 동일한지 확인한다.
- 포맷팅만 바뀐 diff가 생기면 되돌릴 방법을 먼저 찾는다.
- 알려진 한계를 남기는 축약은
cb-simplify: <ceiling>; revisit when <trigger>로 표시한다. - 동작 변경이 발견되면 중단하고 보고한다.
금지:
- 기능 변경
- 스키마/API 변경
- 새 dependency 추가
- 단일 구현 abstraction/factory/wrapper 생성
- 요청 없는 boilerplate/scaffold 추가
- 테스트 약화
- 포맷팅 대량 diff
- 확신이 없을 때 추측(GUESS)으로 변경 — 모르면 그 부분은 SKIP하고 보고한다
- 같은 파일에서 3회 시도 실패 시 강행 — revert 후 중단·보고한다
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 First seen · 29 lines · 20 tokens per session scan A be52673141e3
safe-refactor is a skill published in the GitHub repository ezBuilder/code-brain (11 stars, last pushed 2d ago), licensed Apache-2.0. It adds 20 tokens to every session and 363 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
kayba-stage-3-metrics
Define metrics from Kayba insights, implement them as Python measurement code, run against traces, and iterate until the metrics are clean and meaningful. Trigger when the user says "run stage 3", "define metrics", "build metrics", "compute baselines", or when invoked by the kayba-pipeline orchestrator. Requires…
kayba-stage-4-rubric
Organize computed metrics into a tiered evaluation rubric with leading, lagging, and quality indicators. Trigger when the user says "run stage 4", "build rubric", "tier metrics", or when invoked by the kayba-pipeline orchestrator. Requires eval/baselinemetrics.json and eval/computebaselines.py to exist.
kayba-stage-5-action-plan
Triage each insight into discard/code-fix/prompt-fix and produce a prioritized action plan with specific recommendations. Trigger when the user says "run stage 5", "make action plan", "triage skills", or when invoked by the kayba-pipeline orchestrator. Requires eval outputs from stages 1-4.
kayba-stage-6-hitl
Human-In-The-Loop gate that presents the action plan with full context, collects an informed approval/modification/rejection decision, and records the outcome. Trigger when the user says "run stage 6", "HITL review", "approve action plan", or when invoked by the kayba-pipeline orchestrator. Requires eval/actionplan.md…
kayba-stage-2-domain-context
Gather domain context about the repository and agent — system prompt, tool definitions, domain docs, and behavior patterns from traces. Trigger when the user says "run stage 2", "gather context", "domain context", or when invoked by the kayba-pipeline orchestrator.
kayba-stage-7-fixer
Implement the approved fixes from the action plan and log all changes. Trigger when the user says "run stage 7", "implement fixes", "apply action plan", or when invoked by the kayba-pipeline orchestrator. Requires eval/actionplan.md to exist.