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 agentmods add skills/jabrena/plinth/056-design-avoid-breaking-changesnpx skills add jabrena/plinth --skill 056-design-avoid-breaking-changesgit clone --depth 1 https://github.com/jabrena/plinthWrote 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/jabrena/plinth/056-design-avoid-breaking-changes)<a href="https://agentmods.dev/skills/jabrena/plinth/056-design-avoid-breaking-changes"><img src="https://agentmods.dev/badge/skills/jabrena/plinth/056-design-avoid-breaking-changes.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 | $0.00106 | $0.00845 |
| Opus 5 | $0.00053 | $0.00423 |
| Sonnet 5 | $0.00021 | $0.00169 |
| Haiku 4.5 | $0.00011 | $0.00085 |
Grade A, and why
056-design-avoid-breaking-changes 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 6d 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 — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Avoid Breaking Changes
Review planned repository changes for breaking-change and compatibility risk before implementation or release promotion. This is an interactive SKILL.
What is covered in this Skill?
- Command contract compatibility: names, inputs, owning agents, outputs, safeguards, installer registration, and command inventories
- Skill routing compatibility: identifiers, metadata, descriptions, triggers, references, generated local output, and acceptance coverage
- Generated-output ownership: XML/source files versus
.agents/skills, publicskills/,.cursor/commands,.cursor/rules, anddocs/ - Source and generator contracts: XML, XInclude, XSLT, Maven modules, schema expectations, and module validation
- README, localized README, changelog, migration, and deprecation guidance
- External and runtime contracts: APIs, schemas, data formats, configuration keys, persistence, CLI behavior, and CI expectations
- Structured compatibility reports with severity-ranked findings and validation guidance
Constraints
Keep the review evidence-based, read-only, and scoped to compatibility risk unless the user explicitly asks for implementation.
- MUST read
references/056-design-avoid-breaking-changes.mdbefore producing compatibility guidance - MUST identify the source artifacts reviewed and the compatibility surfaces considered
- MUST distinguish confirmed breaking changes, potential risks, non-breaking changes, and unknowns that need maintainer decision
- MUST include migration, deprecation, validation, or release-note guidance for intentional breaking changes
- MUST respect repository source ownership: edit XML and source docs, regenerate generated output through documented workflows, and avoid direct generated-output edits unless the repository explicitly owns that file
- MUST NOT modify plans, specs, source files, generated outputs, or issue descriptions during review unless the user explicitly requests implementation
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.
- 6d ago First seen · 69 lines · 106 tokens per session scan A f393e70d5b13
056-design-avoid-breaking-changes is a skill published in the GitHub repository jabrena/plinth (435 stars, last pushed yesterday), licensed Apache-2.0. It adds 106 tokens to every session and 845 once invoked, about $0.0005 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
session-deep-dive
Deep qualitative analysis of high-signal sessions. Spawns subagents with v2 template, synthesizes patterns, compares against known findings. Use after /session-scan.
brainstorm
Brainstorm Elixir/Phoenix features — explore ideas, compare approaches, gather requirements. Use when vague idea, not sure how to approach, or want to discuss before plan.
ecto-patterns
Ecto patterns — schemas, changesets, queries, migrations, Multi, associations, preloads, upserts. Use when editing Repo calls, Ecto.Query, or schema fields. Skip for Ash.
pseudocode-to-java-code
Converts pseudocode descriptions and algorithm specifications into complete, executable Java code. Use this skill when you need to implement algorithms from pseudocode, translate algorithm descriptions to Java, generate Java code from specifications, convert textbook algorithms to working code, or create executable…
button-states
Every interactive element needs a complete set of visual states — rest, hover, active/pressed, focus, disabled, and loading. States should be derived algorithmically from the base colour, not chosen arbitrarily. Use when designing buttons, links, inputs, or any clickable component.
form-design
Forms have three layers of guidance: helper text below the input explains what to enter, placeholder shows the expected format, and validation confirms correctness. Real-time validation for complex inputs. Submit enables only when the form is valid. Use when designing or reviewing any form, input field, or data entry…