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-gemini-cli-extension --skill refactor-break-bw-compatgit clone --depth 1 https://github.com/OutlineDriven/odin-gemini-cli-extensionWrote 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-gemini-cli-extension/refactor-break-bw-compat)<a href="https://agentmods.dev/skills/outlinedriven/odin-gemini-cli-extension/refactor-break-bw-compat"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-gemini-cli-extension/refactor-break-bw-compat/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-gemini-cli-extension/refactor-break-bw-compat"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-gemini-cli-extension/refactor-break-bw-compat.svg" alt="Reviewed on agentmods" width="80" 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 10d 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.
This is a copy
100% identical to refactor-break-bw-compat — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
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.
- 10d 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-gemini-cli-extension (5 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. It is 100% identical to refactor-break-bw-compat, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
design
Set visual and interaction direction for any UI surface (web, React, TUI, CLI, desktop, Qt, design-system tokens) before any UI code. Direction-first: generates 3-4 distinct directions via verbalized sampling, picks one via per-axis single-select, then derives palette, typography, spacing, motion budget. Loads when…
askme
Verbalized Sampling (VS) protocol for intent exploration before planning, mode-aware. Default exhaustive runs full VS; collaborative runs tip-sharing dialogue; adversarial walks the design tree one fork at a time. Auto-detects from phrasing ("help me refine" → collaborative, "poke holes" → adversarial); override via…
grill-ai-mastery
Hybrid interview that probes AI-engineering mastery by tip-vocabulary depth — entity referencing, loop closure, observability, harness improvement — not by token usage or LOC. Start collaborative (two-way tip exchange), escalate to adversarial probing when depth is lacking. Trigger when the user says "interview me on…
grill-me
Adversarial relentless interview against any plan or design until shared understanding is reached. Walk the decision tree, resolve dependencies one answer at a time, recommend a default per question. Trigger when the user says "grill me", "stress-test this", "interview me about this design", or otherwise asks for…
git-branchless
Enforce idiomatic git-branchless during planning and executing tasks — detached-HEAD-first work, in-memory rebase via git move, event-log recovery via git undo, deferred branch creation, speculative-merge git sync for base updates. Use when planning or executing multi-commit work, history rewrites, stack edits…
proof-driven
Proof-driven development. Use when implementing with formal verification using property-based testing, theorem proving, or proof tactics; zero unproven property policy enforced.