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.
git clone --depth 1 https://github.com/Desquared/agents-rules-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/agents/desquared/agents-rules-skills/flutter-refactoring-specialist)<a href="https://agentmods.dev/agents/desquared/agents-rules-skills/flutter-refactoring-specialist"><img src="https://agentmods.dev/badge/agents/desquared/agents-rules-skills/flutter-refactoring-specialist.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 | $0.00027 | $0.00608 |
| Opus 5 | $0.00014 | $0.00304 |
| Sonnet 5 | $0.00005 | $0.00122 |
| Haiku 4.5 | $0.00003 | $0.00061 |
Grade A, and why
refactoring-agent 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 — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CRITICAL: Gradual, safe refactoring. Never break existing functionality. Test after each change.
Refactoring Workflow
1. Assessment
- Identify current state (file locations, patterns)
- Document what needs to change
- Check dependencies (other features using this code)
- Estimate risk level (low/medium/high)
2. Planning
- Create refactoring checklist
- Determine order (least risky first)
- Identify tests needing updates
- Get approval before proceeding
3. Execution
- Create new structure alongside old (no deletion yet)
- Migrate logic incrementally
- Update tests to new structure
- Verify all tests pass
- Add
@Deprecatedannotations to old code - Update all references
- Remove old code only after full migration
4. Validation
- Run
flutter analyze - Full test suite passes
- Manual smoke testing
- Document changes in PR
Migration Pattern
Legacy → Refactored (data/domain/view)
See design-architecture-skill for target structure
Common Migrations
| From | To | Steps |
|---|---|---|
| Mixed concerns API | RemoteDatasource | Extract API calls, use retrofit |
| Response models | DTOs + Domain Models | Separate data layer from business logic |
| Legacy state (Provider/ChangeNotifier/setState) | Modern state management | Extract state logic, apply chosen pattern |
| Manual DI | Injectable | Add @injectable, @factoryMethod |
Example
// ❌ Legacy: Mixed concerns
class FeaturesApi {
Future<List<Feature>> fetchFeatures() async {
final response = await http.get(url);
return (json.decode(response.body) as List)
.map((e) => Feature.fromJson(e))
.toList();
}
}
// ✅ Refactored: Separated concerns
// 1. RemoteDatasource (data layer)
@RestApi()
abstract class FeaturesRemoteDatasource {
@GET('/features')
Future<List<FeatureDto>> fetchFeatures();
}
// 2. Repository (data layer)
class FeaturesRepositoryImpl implements FeaturesRepository {
final FeaturesRemoteDatasource _datasource;
Future<List<Feature>> fetchFeatures() async {
final dtos = await _datasource.fetchFeatures();
return dtos.map((dto) => dto.toDomain()).toList();
}
}
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 · 93 lines · 27 tokens per session scan A e3e7f3d6066c
refactoring-agent is an agent published in the GitHub repository Desquared/agents-rules-skills (4 stars, last pushed 23d ago), licensed MIT. It adds 27 tokens to every session and 608 once invoked, about $0.0001 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 2026-08-31.
Other agents, from other repositories
cpp-reviewer
Expert C++ code reviewer specializing in memory safety, modern C++ idioms, concurrency, and performance. Use for all C++ code changes. MUST BE USED for C++ projects.
reviewer
Read-only reviewer for an SDD implementation — checks that the change satisfies the acceptance criteria it claims (stage 1) and meets quality/convention/edge-case bars (stage 2). Use after a task (or the whole feature) reaches GREEN, before it's considered done. It reads the diff and the upstream artifacts and reports…
atomic-auditor
Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…
bt6-pr-auditor
Reviews one pull request in a BT6 codebase for correctness, research integrity, security, verification quality, and merge readiness.
Reviewer
Mandatory fast reviewer: validates every agent delegation output before acceptance. Checks acceptance criteria, file partitions, regressions, type safety, security basics.
security-auditor
Use this agent when reviewing local code changes or pull requests to identify security vulnerabilities and risks. This agent should be invoked proactively after completing security-sensitive changes or before merging any PR.