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/l3digitalnet/claude-code-plugins/generategit clone --depth 1 https://github.com/L3DigitalNet/Claude-Code-PluginsWhat 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 | $0.00037 | $0.01073 |
| Opus 5 | $0.00018 | $0.00536 |
| Sonnet 5 | $0.00007 | $0.00215 |
| Haiku 4.5 | $0.00004 | $0.00107 |
Grade A, and why
generate 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 yesterday.
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 — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/qt-suite:generate — AI Test Generation
Generate unit tests for this Qt project. When an argument is provided, generate tests for that specific file or class. When no argument is provided, scan the project to identify the files most in need of tests.
Step 1: Identify Targets
If an argument was provided (e.g., /qt-suite:generate src/calculator.py):
- Use the argument as the target file or class name
- Find the file with Glob if only a filename was given
If no argument was provided:
- Read
.qt-test.jsonif present to determineproject_typeandtest_dir - Detect project type by checking for
CMakeLists.txt(C++) orpyproject.toml/setup.cfg(Python) - Use Glob to find all source files:
- Python:
**/*.py(excludingtests/,__init__.py, migration files) - C++:
**/*.cppand**/*.h(excludingtests/,moc_*,ui_*,build/)
- Python:
- For each source file, check if a corresponding test file exists:
- Python:
tests/test_<module>.pyforsrc/<module>.py - C++:
tests/<name>_test.cpportests/test_<name>.cppforsrc/<name>.cpp
- Python:
- Prioritize files with no test file at all, then files with low complexity coverage (look for classes with multiple public methods but few or no tests)
- Present the top 3 candidates and select the best target. Prefer business logic classes over utility/helper files.
Step 2: Read and Analyze the Source File
Read the target source file completely. Identify:
- Class names and their public interface
- Methods and their signatures, parameters, return types
- Side effects: file I/O, signals emitted, state mutations
- Edge cases visible from the code: null checks, boundary conditions, exception paths
- Qt-specific elements: signals, slots, widget interactions, model overrides
Step 3: Check Existing Tests
If a test file already exists for this source:
- Read it to understand existing coverage
- Focus generated tests on uncovered methods and edge cases
- Do not duplicate tests that already exist
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.
- yesterday First seen · 102 lines · 37 tokens per session scan A 5935fa367ec2
generate is a command published in the GitHub repository L3DigitalNet/Claude-Code-Plugins (6 stars, last pushed 2d ago), licensed MIT. It adds 37 tokens to every session and 1,073 once invoked, about $0.0002 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 commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.