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 refactor-break-compatgit 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/refactor-break-compat)<a href="https://agentmods.dev/skills/outlinedriven/odin-claude-plugin/refactor-break-compat"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-claude-plugin/refactor-break-compat.svg" alt="Measured on agentmods" 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 | $0.01029 |
| Opus 5 | $0.00020 | $0.00515 |
| Sonnet 5 | $0.00008 | $0.00206 |
| Haiku 4.5 | $0.00004 | $0.00103 |
Grade A, and why
refactor-break-compat 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 yesterday.
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 — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Breaking refactors
Contract
| Field | Bound contract |
|---|---|
| Trigger | Modernizing APIs, removing compat shims, killing feature flags, rewriting a subsystem cleanly. |
| Authority | Human-gated: requires explicit human invocation, previewing target and consequence before any irreversible deletion; otherwise reversible local: writes only VCS-tracked refactor targets; rollback is version control. No remote mutation. |
| Side effect | Deletes compat/adapter/flag code and rewrites every caller and test wholesale; local-delete-unrecoverable. |
| Done | Zero-residue grep, all callers on new contract, tests green on new behavior (exit 0). |
Refusals
- Additive refactors that keep the old path: rejected. This skill demolishes the old path. Use a regular refactor if the old path must survive.
- Shipping the intermediate state (half old, half new): rejected. Finish or revert to the version-control baseline.
- Widening scope beyond the demolition manifest: rejected. Do not widen scope to resolve a finding.
Inputs
- Old API surface (required): the compat shims, legacy adapters, feature flags, version gates, and backward-compatible interfaces to demolish.
- New API surface (required): the target contract every caller must adopt.
- Scope (optional): file or module boundaries; when omitted, the blast-radius map determines scope.
Procedure
- Map the blast radius. Enumerate every file, module, and caller of the old shape using
ast-greporrg. This is the demolition manifest. Done when: the demolition manifest is complete. - Preview and confirm the demolition. Present the demolition manifest and the consequences to the user: every file and caller that will be deleted or rewritten, which tests will change, and which flags or config will be removed. Wait for explicit human confirmation. Do not proceed without it. Done when: the user confirms the demolition.
- Delete the old path. Remove compat layers, adapters, legacy branches, and flags used only by the old path. Do not delete a flag that also controls the replacement or another live path. No commenting out. Delete. Done when: the old path is deleted from every file in the manifest.
- Rewrite every caller to the new contract. Migrate all references from step 1. After each batch, run the strongest static enumerator the project has (compiler or typechecker, including opt-in:
mypy,pyright,tsc --checkJs, Sorbet). Never sufficient alone: no static pass sees reflective, dynamically dispatched, string-constructed, or generated references, nor code excluded from the build. Enumerate those by hand and name them in the report. Done when: every caller in the manifest is on the new contract and the static enumerator passes. - Rewrite tests to the new truth. Update assertions to the new behavior. Delete tests whose entire purpose was the old behavior. Add tests for the new contract where coverage is now thin. Done when: tests assert the new behavior and the old-behavior tests are deleted.
- Exterminate ghosts. Grep for string references, config keys, env vars, doc links, error messages, and import paths naming the old API. Zero survivors. Done when: the grep returns nothing.
- Strip dead weight. Remove imports, packages, dependencies, types, and dead files that only the old path needed. Done when: no dead weight from the old path remains.
- Verify zero residue. A search for every old symbol, flag, and format name returns nothing. If it returns anything, return to step 4. Done when: the zero-residue search returns nothing.
What ships with it
1 file 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.
- yesterday Changed · +1 lines · -17 tokens per session 6999310ef391
- 4d ago First seen · 51 lines · 57 tokens per session scan A 602a6dab6969
refactor-break-compat is a skill published in the GitHub repository OutlineDriven/odin-claude-plugin (35 stars, last pushed today), licensed Apache-2.0. It adds 40 tokens to every session and 1,029 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 2026-09-04.
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…
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…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…