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 humanerd-drew/opencode-drewgent --skill llm-model-migrationgit clone --depth 1 https://github.com/humanerd-drew/opencode-drewgentWrote 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/humanerd-drew/opencode-drewgent/llm-model-migration)<a href="https://agentmods.dev/skills/humanerd-drew/opencode-drewgent/llm-model-migration"><img src="https://agentmods.dev/badge/skills/humanerd-drew/opencode-drewgent/llm-model-migration.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 5.1 | $0.00000 | $0.07818 |
| Opus 5 | $0.00000 | $0.03909 |
| Sonnet 5 | $0.00000 | $0.01564 |
| Haiku 4.5 | $0.00000 | $0.00782 |
Grade A, and why
llm-model-migration 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 — 515 lines — stays where its author put it; the contents beside it link to each section on GitHub.
name: llm-model-migration description: LLM provider가 default model을 업데이트(M2.7→M3, GPT-4→GPT-5, claude-3.5→3.7)하거나 pricing/Token Plan을 변경했을 때 코드/문서/카탈로그를 일관되게 마이그레이션하는 표준 절차. scope 분해 → grep inventory → catalog+production+docs 병렬 patch → 3단계 verification (AST, runtime, grep) → out-of-scope flagging → memory 영구 저장. title: LLM Model Migration — Provider Default Update domain: software-development space: growth type: workflow tags: [llm, model-migration, provider-update, token-plan, {{AGENT_NAME_LOWER}}] created: 2026-06-01 updated: 2026-06-01 links:
- "[[@memory/growth/INTEGRATION_PROTOCOL]]"
- "[[@identity/SELF_MODEL]]"
- "[[@identity/brain/{{AGENT_NAME}}-brain/P0-brainstem/禁/禁task_qa_gate.neuron]]"
- "[[@identity/brain/{{AGENT_NAME}}-brain/P0-brainstem/禁/禁blind_write.neuron]]"
- "[[@identity/brain/{{AGENT_NAME}}-brain/P0-brainstem/禁/禁karpathy_coding_principles.neuron]]"
- "[[@identity/brain/rules]]"---
LLM Model Migration — Provider Default Update
LLM provider가 default model을 업데이트했을 때 (M2.7→M3, GPT-4→GPT-5, claude-3.5→3.7 등) 코드/문서/설정을 일관되게 마이그레이션하는 표준 절차.
트리거 조건
다음 중 하나라도 해당되면 이 스킬을 로드:
- Provider 모델 업데이트 발표 (new default)
- Token Plan / pricing 변경 (per-call 정액제 → input/output 단가제 등)
- 모델 context window 변경 (8K → 1M 등)
- Legacy catalog 정리 (구 모델 deprecation)
1단계: Scope 확정 (사용자 입력 파싱)
사용자가 제시한 scope를 명확히 분리:
- In-scope files: 사용자가 명시한 파일 (예: "production code 4개 파일")
- Catalog/registry: model_metadata.py 같은 lookup table
- Docs: providers.md, SKILL.md, README, ARCHITECTURE
- Comments: source code 주석/문서
- Out-of-scope candidates: scope 밖이지만 영향 받을 수 있는 파일 (orchestrator, test fixture 등)
⚠️ Scope 밖 후보는 사용자에게 보고만 하고 변경하지 않는다 — silently 바꾸면 사용자의 의도(intent)를 무시하게 된다.
2단계: 재고 (Inventory) — grep으로 모든 참조 수집
# In-scope + catalog + docs
grep -rn "M2.7" --include="*.py" --include="*.md" \
scripts/ plugins/ P0-brainstem/ agent/ \
website/docs/ skills/ CHANGELOG.md
2-1. Multi-source file discovery (필수)
{{AGENT_NAME}} vault는 같은 파일이 여러 위치에 복사돼있을 수 있다. catalog/config 단일 파일로 가정하면 안 됨:
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 · 515 lines · 0 tokens per session scan A bd12c20a01a0
llm-model-migration is a skill published in the GitHub repository humanerd-drew/opencode-drewgent (2 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 7,818 tokens. 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 2026-09-03.
Other skills, from other repositories
agent-platform-rag-engine-management
Manage and query Agent Platform RAG Engine Corpora and retrieve grounded contexts using the Google GenAI SDK. Use when listing RAG corpora or files, inspecting a corpus, retrieving contexts, or generating content grounded in a RAG corpus. Do not use for standard database queries (use SQL/Spanner skills), Google…
agent-platform-model-registry
Agent Platform Model Registry Management. Use when you need to upload, list, describe, update, or delete machine learning models (and their versions) in the Agent Platform Model Registry. Don't use for model training, model deployment to endpoints, or managing non-Agent Platform models.
foundry-config-setup
Resolve missing setup caused by a hardcoded Foundry project endpoint or model in a sample. Use when a sample fails because it uses a placeholder/hardcoded projectendpoint (for example "https://your-project.services.ai.azure.com") or a hardcoded model instead of reading them from the environment.
google-cloud-solution-agentic-analytics-spark-knowledge-catalog
Discovers requirements and generates guidance to design and deploy a governed, secure agentic-analytics solution for data that's distributed across Google Cloud, other cloud providers, or on-premises. Data that's outside Google Cloud (such as data from Databricks, Snowflake, Salesforce, SAP, or Oracle systems) is…
training-check
Interactively monitor training metrics from the current Codex session, periodically checking WandB or fallback logs for NaN, divergence, plateaus, and broken runs.
nemo-automodel-launcher-config
Configure NeMo AutoModel job launches for interactive runs, Slurm clusters, and SkyPilot cloud execution.