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 OutlineDriven/odin-claude-plugin --skill deprecate-and-migrategit clone --depth 1 https://github.com/OutlineDriven/odin-claude-pluginWrote 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/outlinedriven/odin-claude-plugin/deprecate-and-migrate)<a href="https://agentmods.dev/skills/outlinedriven/odin-claude-plugin/deprecate-and-migrate"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-claude-plugin/deprecate-and-migrate/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/outlinedriven/odin-claude-plugin/deprecate-and-migrate"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-claude-plugin/deprecate-and-migrate.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00040 | $0.01192 |
| Opus 5 | $0.00020 | $0.00596 |
| Sonnet 5 | $0.00008 | $0.00238 |
| Haiku 4.5 | $0.00004 | $0.00119 |
Grade A, and why
deprecate-and-migrate 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 5d 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 — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Deprecate and migrate
Contract
| Field | Bound contract |
|---|---|
| Trigger | Removing old code, migrating users to a replacement, or deciding whether to maintain or sunset a system. |
| Authority | Reversible local: writes only VCS-tracked code, config, and docs (destructive; the exact changed set is shown before any mutation); rollback is version control. No remote mutation. |
| Side effect | Builds or verifies a replacement, updates consumers and docs, and removes obsolete VCS-tracked code/config/docs only after migration evidence clears. |
| Done | All consumers use the production-proven replacement, old usage is zero, obsolete code/config/docs are removed, and rollback/monitoring evidence is recorded. |
Inputs
- The deprecated system: its VCS-tracked code, tests, config, and docs, and the full set of consumers. Must be supplied.
- A replacement that is production-proven and covers every critical use case of the old system, or a decision to build one first. Must exist before any removal.
- Current usage evidence: metrics, logs, and dependency analysis proving active usage. Must be supplied to prove zero usage before removal.
- Optional: a hard removal deadline (compulsory deprecation) and migration tooling.
Procedure
- Bound scope. List the deprecated system's VCS-tracked files (code, tests, config, docs) and every consumer. Show this exact set before any mutation; do not mutate untracked targets. Done when: the tracked file and consumer set is shown before mutation.
- Make the maintain-or-sunset decision. Answer, in order: does the system still provide unique value (if yes, maintain it and stop); how many consumers depend on it; does a production-proven replacement exist (if no, build it first); what is each consumer's migration cost; what is the ongoing maintenance cost of not deprecating. Stop at maintain if the system still provides unique value. Done when: maintain or sunset is chosen from the recorded evidence.
- Choose the deprecation pressure. Default to advisory: warnings, documentation, and nudges, with users migrating on their own timeline. Use compulsory (a hard removal deadline plus shipped migration tooling, documentation, and support) only when maintenance cost or security risk forces it. A deadline alone is not a migration. Done when: advisory or compulsory pressure is chosen with its condition stated.
- Verify the replacement is production-proven and covers every critical use case of the old system, with a migration guide containing concrete steps and examples. No deprecation proceeds without a working, production-proven alternative. Done when: every critical use case has production evidence and migration guidance.
- Announce. Write a deprecation notice naming status, replacement, removal date, and reason, plus the migration guide. Done when: the notice and guide contain all named fields.
- Migrate consumers one at a time. For each consumer: identify all touchpoints with the old system, update to the replacement, verify behavior matches via tests and integration checks, remove old-system references, and confirm no regressions. For a formal cutover, sequence consumers under one approved rollback boundary; never leave the old and new paths active together after the cutover. The Churn Rule: the owner of deprecated infrastructure owns migrating every consumer in the same cutover; do not shift migration work to consumers or carry a compatibility path. Done when: every consumer uses only the replacement and passes its checks.
- Prove zero active usage via metrics, logs, and dependency analysis. Done when: all three evidence sources show zero usage.
- Remove the old system. Delete the code, associated tests, documentation, configuration, and the deprecation notices. Commit each removal so version control is the recovery path. Done when: obsolete tracked artifacts are removed in recoverable commits.
- Record rollback and monitoring evidence: the commit range that reverts the removal, and the metric/log watch set that confirms no consumer regressed after removal. Done when: the revert range and watch set are recorded.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 5d ago Changed · -18 tokens per session 789392a9c3f6
- 7d ago Changed · -118 lines · +29 tokens per session 7487fa59699b
- 11d ago First seen · 165 lines · 29 tokens per session scan A 5efc31fe22f1
deprecate-and-migrate is a skill published in the GitHub repository OutlineDriven/odin-claude-plugin (35 stars, last pushed 2d ago), licensed Apache-2.0. It adds 40 tokens to every session and 1,192 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…