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-codex-plugin --skill refactor-break-bw-compatgit clone --depth 1 https://github.com/OutlineDriven/odin-codex-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-codex-plugin/refactor-break-bw-compat)<a href="https://agentmods.dev/skills/outlinedriven/odin-codex-plugin/refactor-break-bw-compat"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-codex-plugin/refactor-break-bw-compat.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 | $0.00040 | $0.01041 |
| Opus 5 | $0.00020 | $0.00521 |
| Sonnet 5 | $0.00008 | $0.00208 |
| Haiku 4.5 | $0.00004 | $0.00104 |
Grade A, and why
refactor-break-bw-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 7d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- refactor-break-bw-compat — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Breaking Refactors — Freedom Through Structure
Compatibility layers are coupling debt with interest. Every compat shim is a decision deferred, not a decision avoided. Break cleanly, break once, break with evidence.
Principles
- No half-measures. A partial migration is worse than no migration — it doubles the surface area and confuses every reader.
- One migration direction. Old-to-new only. Never add new-to-old adapters; that entrenches the old path.
- Blast radius awareness. Map every consumer before removing anything. Surprise breakage is a planning failure, not a courage signal.
- Dead code is a lie. "Just in case" code is not dead — it actively misleads readers about what the system does.
- Compat shims are temporary. If a shim has no removal date, it is permanent. If it is permanent, it is architecture. Decide which.
Reconnaissance Checklist
Before breaking anything, find and catalog:
@deprecated/#[deprecated]/warnings.warnmarkers — especially ones without removal versions- Version-gated code paths (
if version >= X, feature flags,#[cfg(feature = "legacy")]) - Adapter / shim / bridge / wrapper layers that translate between old and new interfaces
- Dual serialization formats (v1/v2 JSON schemas, protobuf
oneofwith legacy fields) - Tests that exist solely to validate backward-compatible behavior
- Configuration keys that toggle between old and new behavior
- Re-export / forwarding modules that alias old paths to new locations
- Changelog entries promising deprecation timelines
Decision: Break or Not?
| Signal | Break | Do NOT Break |
|---|---|---|
| Zero external consumers | Yes | — |
| Single internal consumer, you own it | Yes | — |
| Well-tested, high coverage | Yes | — |
| Clear new path exists | Yes | — |
| External/public API with unknown consumers | — | Not without migration plan |
| No tests covering the boundary | — | Write tests first, then break |
| Multiple consumers, unclear ownership | — | Map consumers first |
| Compat layer under active use by migration-in-progress | — | Finish migration first |
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.
- 7d ago First seen · 80 lines · 40 tokens per session scan A 023ae21fef21
refactor-break-bw-compat is a skill published in the GitHub repository OutlineDriven/odin-codex-plugin (15 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 40 tokens to every session and 1,041 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
git-guardrails-claude-code
Install a Claude-Code PreToolUse hook that blocks destructive git commands (push variants including force-push, hard reset, force clean, branch -D, checkout/restore overwrites) before Bash runs them. Use when the user wants git safety rails, force-push prevention, or repository-wipe protection.
duet
Two-party posture — user as director, agent as executor; every fork, tradeoff, or choice surfaced via batched AskUserQuestion with a recommended default. Use when the user invokes /duet, says "ask before" / "pair with me" / "human-in-the-loop", or for aesthetic/architectural/irreversible decisions.
explore
Read-only codebase exploration: discovery, structural reading, and emission of architecture/pattern/tooling/dependency summaries. Use to understand existing code, map files, trace function flow, locate symbols, or build pre-implementation context. Uses a staged 1/3/5 Explore-agent escalation protocol scaled to scope.…
deps-upgrade
Dependency-upgrade campaign — outdated scan, batch-by-severity, breaking-change remediation, lockfile audit. Use when CVEs require remediation, when a major upstream version lands, when stack compatibility forces a sweep, or on a scheduled (quarterly) hygiene cadence. CVE-driven bumps consume security audit findings…
type-driven
Type-driven development. Use when developing with refined types, state machines encoded in types, or proof-carrying types; enforces totality and exhaustive pattern matching.
design-by-contract
Design-by-Contract (DbC) development. Use when implementing with formal preconditions, postconditions, and invariants across any language.