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 ariaramin/flutter-skills --skill freezed-production-engineeringgit clone --depth 1 https://github.com/ariaramin/flutter-skillsWrote 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/ariaramin/flutter-skills/freezed-production-engineering)<a href="https://agentmods.dev/skills/ariaramin/flutter-skills/freezed-production-engineering"><img src="https://agentmods.dev/badge/skills/ariaramin/flutter-skills/freezed-production-engineering/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/ariaramin/flutter-skills/freezed-production-engineering"><img src="https://agentmods.dev/badge/skills/ariaramin/flutter-skills/freezed-production-engineering.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 | $0.00133 | $0.04366 |
| Opus 5.5 | $0.00053 | $0.01746 |
| Sonnet 5.5 | $0.00027 | $0.00873 |
| Haiku 4.5 | $0.00013 | $0.00437 |
Grade A, and why
freezed-production-engineering 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.
How it starts
The opening of the file, as written. The whole thing — 422 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Freezed Production Engineering
Mission
Choose the lowest-complexity Dart modeling mechanism that provides the semantics the repository actually needs. Use Freezed when generated immutable value semantics, copying, serialization integration, or payload-bearing sealed variants materially reduce maintenance or correctness risk. Prefer native Dart when it is equally safe and clearer.
Do not optimize for the number of generated classes. Optimize for explicit semantics, stable contracts, repository consistency, predictable runtime behavior, and maintainability.
Non-negotiable rules
- Inspect the repository before changing models or generator syntax.
- Verify the Dart/Flutter SDK and the resolved
freezed,freezed_annotation,json_serializable,json_annotation, andbuild_runnerversions. - Decide whether Freezed is justified before adding
@freezed. - Treat persisted or serialized JSON as an external contract, not incidental model syntax.
- Treat generated equality and
hashCodeas real runtime work, especially for large/deep collections. - Treat Freezed collection protection as unmodifiable access, not recursive deep immutability.
- Never edit
*.freezed.dartor*.g.dartmanually. - Regenerate after source/annotation/configuration changes.
- Prefer modern Dart
switch/patterns for new union consumption when the repository supports them. - Do not create duplicate DTO/entity/model layers without an independently evolving semantic boundary.
- Do not use
@Assertas the sole production validation for untrusted or security-sensitive values. - Do not disable equality, copying, or collection protection merely to make mutation easier; reconsider whether Freezed is the right model.
- Do not attribute a performance issue to Freezed until the expensive operation is identified and measured.
- Treat major Freezed/build-tool upgrades as migrations.
Reference routing
Read only the reference needed for the task:
references/01-selection-immutability-copying.md— choosing Freezed vs native Dart; dependencies; immutable data classes; collection ownership; equality/hash;copyWith; constructors; defaults; classic classes; unions and native patterns.references/02-unions-json-configuration.md— JSON architecture; DTO examples; nested JSON; defaults/nullability; enums;JsonConverter; union discriminators/fallbacks; generics; interfaces/mixins; Freezed/build configuration; state modeling; DTO/domain/persistence boundaries.references/03-performance-build-tooling.md— runtime/memory/large-collection analysis; build-time cost; code size; build_runner;--only-check; generated-file ownership; CI policy; major upgrades; primary constructors; stale generation and cache diagnostics.references/04-testing-antipatterns-decisions.md— testing strategy; serialization fixtures; anti-patterns; native-vs-Freezed, model-category, and serialization decision tables; performance/build/review checklists.references/05-workflow-completion-sources.md— full implementation workflow; completion criteria; fast decision algorithm; good rejections/strong candidates; annotation/generated-code stance; source-grounded conclusions and source list.
What ships with it
5 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.
- 7d ago First seen · 422 lines · 133 tokens per session scan A da52034d508e
freezed-production-engineering is a skill published in the GitHub repository ariaramin/flutter-skills (6 stars, last pushed 7d ago), licensed MIT. It adds 133 tokens to every session and 4,366 once invoked, about $0.0005 per session on Opus 5.5. 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 2026-10-11.
Other skills, from other repositories
ia-verification-before-completion
Enforces fresh verification evidence before any completion claim. Use when about to claim "tests pass", "bug fixed", "done", "ready to merge", handing off work, or before editing when a request has ambiguous scope.
ia-debugging
Systematic root-cause debugging with verification. Use for errors, stack traces, broken tests, flaky tests, regressions, or anything not working as expected. For validating bug reports before fixing, use bug-reproduction-validator agent.
test-failure-explorer
Import and query an existing Vitest 3.2 JSON report to explore test failures, file-level errors and original diagnostic evidence.
code-review
Reviews code for bugs, security issues, and best practices.
adversarial-reviewer
Stress-test a code change for concrete correctness defects, unsafe assumptions, and failure modes. Use when the user explicitly asks for an adversarial review, a deep bug hunt, or to tear a change apart, or to check your own change before submitting it. Do not use for ordinary review, style feedback, or general…
omh-verification-gate
This is an OMH verification-gate workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).