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/evansims/openfga-mcp/testgit clone --depth 1 https://github.com/evansims/openfga-mcpWhat 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 | $0.00323 |
| Opus 5 | $0.00000 | $0.00161 |
| Sonnet 5 | $0.00000 | $0.00065 |
| Haiku 4.5 | $0.00000 | $0.00032 |
Grade A, and why
test 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.
What it actually says
Your mission: Achieve a completely clean test suite with zero failures, warnings, or skipped tests.
Execution Order:
- Run unit tests:
composer test:unit - Run integration tests:
composer test:integration - Apply any linter auto fixes:
composer lint:fix - Verify all linters pass after auto fixes:
composer lint
Decision Framework:
When tests fail, determine the root cause:
- Bug in codebase → Fix the underlying code issue
- Flawed test → Fix or remove the problematic test
- Missing dependency/setup → Address the missing requirement
Test Standards:
- Framework: All tests must use Pest syntax exclusively
- Clarity: Tests should be self-describing - no unnecessary comments
- Quality: Clean, readable test code that speaks for itself
Success Criteria:
- All unit tests pass (no failures, warnings, or skips)
- All integration tests pass (no failures, warnings, or skips)
- All tests follow Pest framework syntax
- All linting rules pass
- Final exit status: 0
Non-Negotiables:
- NEVER skip tests - they either pass or get removed
- Address root causes, not symptoms
- Each test type must complete successfully before moving to the next
- No unnecessary test comments - let the code tell the story
Think systematically about each failure. Is this revealing a genuine issue in our code that users might encounter, or is it a test that no longer serves its purpose? Fix accordingly.
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 · 40 lines · 0 tokens per session scan A 4d3a79ec900f
test is a command published in the GitHub repository evansims/openfga-mcp (10 stars, last pushed 9mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 323 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
rspec
Generate RSpec tests for Ruby classes or methods.
test
Generate Laravel tests with Pest following best practices.
test-ts
Run TypeScript tests for Solana frontends and Anchor programs.
upgrade-livewire
You are a specialized assistant for upgrading Laravel Livewire from version 3 to version 4.
generate-tests
Generate unit or integration tests for Go code following project patterns and coverage targets.
test
Generate tests for the specified code or feature.