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 skills add mrinalwadhwa/fluent --skill review-testsgit clone --depth 1 https://github.com/mrinalwadhwa/fluentWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/mrinalwadhwa/fluent/review-tests)<a href="https://agentmods.dev/skills/mrinalwadhwa/fluent/review-tests"><img src="https://agentmods.dev/badge/skills/mrinalwadhwa/fluent/review-tests/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/mrinalwadhwa/fluent/review-tests"><img src="https://agentmods.dev/badge/skills/mrinalwadhwa/fluent/review-tests.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What 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 5.1 | $0.00036 | $0.00344 |
| Opus 5.5 | $0.00014 | $0.00138 |
| Sonnet 5.5 | $0.00007 | $0.00069 |
| Haiku 4.5 | $0.00004 | $0.00034 |
Grade A, and why
review-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 1mo 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
Purpose
Decide whether the code under review is adequately tested. Identify testable code that lacks tests, and improvements that would make the test suite more likely to catch bugs or the codebase safer to refactor.
Scope
The invoking layer decides what's in scope. For a diff-scoped review, that's the code and tests changed in the diff. For a full-codebase audit, that's the entire codebase and test suite. Check the tests for quality and check the code for tests that should exist but don't.
Method
-
Read the code under review to understand what should be tested.
-
Read
references/tests.mdfor test-writing standards. Read any related guides it points to for the code under review. -
For each in-scope test:
- Read it alongside the code it exercises, its setup and fixtures, and any shared helpers.
- Evaluate against the standards in
references/tests.md. - Identify improvements.
-
Check the code for behavior that lacks tests. For a diff-scoped review, look for changed code paths, edge cases, and error paths that no test covers. For a full-codebase audit, look for significant components with no test coverage.
-
For each improvement, decide if it blocks shipping. Tests that pass without verifying behavior, flaky tests, and testable code shipped without tests typically block. Vague names, duplicated helpers, and style issues typically don't.
The invoking layer may add checks in addition to those above.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 1mo ago First seen · 30 lines · 36 tokens per session scan A e7bbb897769b
review-tests is a skill published in the GitHub repository mrinalwadhwa/fluent (122 stars, last pushed 17d ago), licensed Apache-2.0. It adds 36 tokens to every session and 344 once invoked, about $0.0001 per session on Opus 5.5. 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 skills, from other repositories
e2e
Agentic end-to-end tests with e2e, the e2e runner. Covers scaffolding e2e.config.ts, picking the Playwright browser engine or the agent-device mobile engine, starting the app under test from the config, driving flows with agent.act, judging with agent.assert, agent.waitFor, and agent.extract, pinning values with…
dev-browser
CIEL's framework for browser automation with persistent page state. Navigates URLs, fills forms, takes screenshots, scrapes data, and tests web apps via sandboxed JavaScript scripts.
test_runner
Test execution, coverage analysis, failure diagnosis, re-run strategy.
eval-harness
Formal evaluation framework for CIEL sessions implementing Eval-Driven Development (EDD) principles for autonomous agents.
finishing-a-development-branch
The Finality Layer for CIEL orchestration. Guides the completion of an epic by enforcing global verification, presenting integration options, and handling Git cleanup.
ai-first-engineering
Ciel's operating model for AI-native engineering and agent-friendly architecture.