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 commands/consiliency/flutter-structurizr/implement-next-phasegit clone --depth 1 https://github.com/Consiliency/Flutter-StructurizrWhat 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 | $0.00000 | $0.00662 |
| Opus 5 | $0.00000 | $0.00331 |
| Sonnet 5 | $0.00000 | $0.00132 |
| Haiku 4.5 | $0.00000 | $0.00066 |
Grade A, and why
implement-next-phase 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 2d 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 — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Implementation Command: Implement Next Incomplete Phase
Phase Identification and Analysis
-
Analyze the implementation status in these files:
specs/implementation_status.mdspecs/flutter_structurizr_implementation_spec.md- All phase files in
specs/phase*_implementation_plan.md
-
Identify the lowest-numbered phase that has incomplete tasks (<100% complete)
-
For the identified phase:
- Thoroughly review the specification in
specs/phase{N}_implementation_plan.md - Analyze requirements, dependencies, and implementation approach
- Create a detailed task breakdown of remaining implementation work
- Review original Structurizr code mentioned in specs to understand expected functionality
- Check for recent best practices and lessons learned in CLAUDE.md before starting implementation
- Thoroughly review the specification in
Implementation Strategy
-
Develop a systematic approach to complete the identified phase: Ultra Think
- Prioritize core functionality first
- Break down complex tasks into manageable components
- Ensure compatibility with already implemented phases
- Consider potential name conflicts with Flutter built-ins
- Coordinate with the latest modular parser refactor and alias/type usage guidelines
- Reference the
ai_doc/directory for specific framework and library documentation - Use Web Fetch, Web Search, and Fetch tools to find examples and documentation if not in
/ai_docs- Compile new documentation that you find into a library specific markdown file and save it in
/ai_docsfor future reference
- Compile new documentation that you find into a library specific markdown file and save it in
-
Implementation execution: Think Hard
- Create/modify necessary Dart files to implement required functionality
- Follow clean architecture principles
- Implement all remaining tasks from the phase specification
- Ensure code quality meets project standards
- After each major implementation step, run flutter analyze and flutter test to catch issues early
- Resolve any compilation errors immediately
- Follow existing code patterns and naming conventions
- Handle name conflicts with Flutter built-ins as described in CLAUDE.md
- Document any new best practices or lessons learned during implementation for later inclusion in CLAUDE.md or specs
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.
- 2d ago First seen · 64 lines · 0 tokens per session scan A 447b49ba7a85
implement-next-phase is a command published in the GitHub repository Consiliency/Flutter-Structurizr (7 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 662 tokens. 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 commands, from other repositories
validate
Run lint and build to validate changes.
responsive-design-specialist
Use when a layout breaks between sizes. Arbitrary breakpoints, type that does not scale, images that blow out the grid, or a desktop design retrofitted onto mobile.
compose-test
Run Compose UI tests with Espresso. Verify critical user flows.
app-store-audit
Run an enterprise pre submission compliance audit on an iOS or Android app against Apple App Store and Google Play rejection rules. Pass a project path or run from the project root.
build-verify
Run the full build / test / analyze / format verification pass for this Flutter app.
apollo-status
Show the current Apollo removal migration progress.