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/versoxbt/claude-initial-setup/test-coveragegit clone --depth 1 https://github.com/VersoXBT/claude-initial-setupWhat 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 | $0.00012 | $0.00446 |
| Opus 5 | $0.00006 | $0.00223 |
| Sonnet 5 | $0.00002 | $0.00089 |
| Haiku 4.5 | $0.00001 | $0.00045 |
Grade A, and why
test-coverage 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 — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Test Coverage
Analyze current test coverage, identify gaps, and write tests to achieve at least 80% coverage.
Steps
-
Run the test suite with coverage enabled:
- Detect the test runner (jest, vitest, pytest, go test, etc.).
- Run with coverage flags and capture the coverage report output.
npm test -- --coverage pytest --cov --cov-report=html go test -cover -coverprofile=coverage.out ./... -
Parse the coverage report:
- Identify files below 80% coverage.
- Sort by coverage percentage (lowest first).
- Note which lines and branches are uncovered.
-
Prioritize coverage gaps:
- Focus on business logic and utility functions first.
- Prioritize files with complex branching and error handling.
- Skip auto-generated files, type definitions, and configuration files.
-
Write missing unit tests:
- For each uncovered function, write tests covering:
- Happy path with valid inputs.
- Edge cases (null, undefined, empty, boundary values).
- Error cases (invalid inputs, thrown exceptions).
- Follow existing test patterns and conventions in the project.
- Use descriptive test names that explain the expected behavior.
- For each uncovered function, write tests covering:
-
Write missing integration tests:
- Test API endpoints with valid and invalid requests.
- Test database operations with proper setup and teardown.
- Test interactions between modules.
-
Run tests after writing each batch:
- Verify new tests pass.
- Verify existing tests still pass.
- Re-check coverage numbers.
-
Repeat until all target files are at or above 80% coverage.
If Coverage Cannot Reach 80%
- Check if uncovered code is truly unreachable (dead code) and remove it.
- Check if uncovered code requires complex setup (external services, specific environments) and note it.
- Document any intentional exclusions with coverage ignore comments and justification.
Output
Updated test suite with all tests passing and coverage at or above 80% for target files. Include a before/after coverage summary.
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 · 60 lines · 12 tokens per session scan A 2e026443d565
test-coverage is a command published in the GitHub repository VersoXBT/claude-initial-setup (4 stars, last pushed 3mo ago), licensed MIT. It adds 12 tokens to every session and 446 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 commands, from other repositories
git
Git operations with intelligent commit messages and workflow optimization.
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.
constitution
Create or update the project constitution from interactive or provided principle inputs.