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/nylas/cli/generate-testsgit clone --depth 1 https://github.com/nylas/cliWhat 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 | $0.00017 | $0.00408 |
| Opus 5 | $0.00009 | $0.00204 |
| Sonnet 5 | $0.00003 | $0.00082 |
| Haiku 4.5 | $0.00002 | $0.00041 |
Grade A, and why
generate-tests 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.
What it actually says
Generate Tests
Generate unit or integration tests for Go code.
Patterns: See .claude/shared/patterns/ for templates:
go-test-patterns.md- Unit test patternsintegration-test-patterns.md- CLI integration tests + rate limiting
Agent: See .claude/agents/test-writer.md for autonomous test generation.
Instructions
-
Ask me for:
- Which file/function to test
- Test type: unit or integration
- Specific scenarios to cover (optional)
-
Read the appropriate pattern file for templates.
-
Analyze the code and generate tests following project patterns.
Integration Tests
See .claude/rules/testing.md for location, build tags, and naming. Key additions:
- Always use
skipIfMissingCreds(t)andacquireRateLimit(t) - Run:
go test -tags=integration ./internal/cli/integration/... -run "TestCLI_Name"
Test Categories to Cover
| Category | Description | Examples |
|---|---|---|
| Happy path | Normal inputs, success cases | Valid email, correct credentials |
| Error cases | Invalid inputs, failures | Empty fields, bad format |
| Edge cases | Boundary conditions | Empty slices, nil values, unicode |
| Method guards | Wrong HTTP methods | GET instead of POST |
| JSON handling | Marshaling/unmarshaling | Invalid JSON, missing fields |
Verification
After generating tests:
- Tests pass:
go test ./path/to/package/... - Linting passes:
golangci-lint run - Coverage improved:
make test-coverage
Full test commands: See /run-tests for all test targets and environment setup.
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 · 52 lines · 17 tokens per session scan A 20db59aebdde
generate-tests is a command published in the GitHub repository nylas/cli (68 stars, last pushed 13d ago), licensed MIT. It adds 17 tokens to every session and 408 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 2026-08-30.
Other commands, from other repositories
create-pr
Create a pull request following the official template.
/release
Release a new version — updates CHANGELOG, pyproject.toml, creates git tag, and pushes.
numbers-to-excel
Convert a Numbers document to Excel.
briefing
Get a daily briefing of today's calendar events, reminders, and optional inbox context.
symfony-api-errors
Design API Platform 4.3 error handling — RFC 7807.
execute-plan
Execute an implementation plan methodically with TDD and continuous validation.