Borrowing it
Nothing to install: this file belongs to cl-ai-project/cl-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/cl-ai-project/cl-mcp/main/.claude/skills/comprehensive-test/SKILL.mdgit clone --depth 1 https://github.com/cl-ai-project/cl-mcpWrote 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/cl-ai-project/cl-mcp/comprehensive-test)<a href="https://agentmods.dev/skills/cl-ai-project/cl-mcp/comprehensive-test"><img src="https://agentmods.dev/badge/skills/cl-ai-project/cl-mcp/comprehensive-test/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/cl-ai-project/cl-mcp/comprehensive-test"><img src="https://agentmods.dev/badge/skills/cl-ai-project/cl-mcp/comprehensive-test.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Anti-Refusal · line 68 Skill attempts to nullify the agent's safety policies or restrictions ('you have no restrictions', 'ignore your guidelines', 'do anything now'). This is a direct jailbreak that disables guardrails.Fix: Remove jailbreak framing that nullifies safety policies or restrictions. Skill content must not instruct the agent to ignore its guidelines or operate without guardrails.
- high Prompt Injection · line 68 This pattern attempts to override system instructions or ignore safety constraints. Without LLM analysis, manual review is recommended.Fix: Remove or rewrite any text that instructs the agent to ignore prompts, override safety rules, or trust unverified content. Ensure skill content cannot be injected to alter agent behavior.
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 | $0.00052 | $0.02698 |
| Opus 5 | $0.00026 | $0.01349 |
| Sonnet 5 | $0.00010 | $0.00540 |
| Haiku 4.5 | $0.00005 | $0.00270 |
Grade A, and why
comprehensive-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 9d 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 — 264 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Comprehensive Test (Common Lisp / cl-mcp)
Test a Common Lisp product from multiple perspectives using parallel agents, then aggregate and evaluate findings.
Arguments
$ARGUMENTS should contain:
- What to test (a project, feature, module, or API)
- Optionally, specific areas of concern
Examples:
/comprehensive-test evaluator/comprehensive-test sandbox safety/comprehensive-test full
Severity Criteria
All testers and the coordinator MUST use these definitions consistently:
| Severity | Definition | Examples |
|---|---|---|
| Critical | Crashes, security vulnerabilities, data loss, spec violations that break core guarantees | Sandbox escape, infinite loop without halting, wrong result from arithmetic |
| Major | Incorrect behavior, missing validation, unhelpful error messages, undocumented deviation from spec | Type error not caught, error message missing context, edge case returning wrong value |
| Minor | Style issues, naming inconsistency, documentation gaps, non-idiomatic patterns | Inconsistent predicate naming, missing docstring, redundant code |
Instructions
1. Analyze the Product
Before spawning testers, build a context brief to share with all testers:
- Set project root: Use
fs-set-project-rootwith the working directory to ensure cl-mcp file tools resolve paths correctly - Discover the system: Read the
.asdfile to find the main system name and test system definitions (look fordefsystem "*/tests"or similar patterns) - Load the system: Use
load-systemto load the target system - Read project structure: Use
lisp-read-file(collapsed mode) on key source files to get an overview of exported symbols and modules - Run existing tests: Use
run-testson each discovered test system to establish the baseline - Identify key areas: Use
clgrep-searchto find the main code areas (builtins, evaluator, reader, API, etc.)
Full suite shortcut (Bash fallback for clean process):
rove {system-name}.asd
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.
- 9d ago First seen · 264 lines · 52 tokens per session scan A 897a7f0fcc14
comprehensive-test is a skill published in the GitHub repository cl-ai-project/cl-mcp (84 stars, last pushed today), licensed MIT. It adds 52 tokens to every session and 2,698 once invoked, about $0.0003 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 skills, from other repositories
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
tika-eval-compare
Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".
neuron-evaluation-engineer
Create and run AI evaluations with datasets, assertions, and output drivers in Neuron AI. Use this skill whenever the user mentions evaluation, testing AI systems, creating evaluators, dataset-driven testing, assertion-based validation, or wants to measure AI system performance. Also trigger for tasks involving…
jetson-validate-image
Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.
atmos-validation
Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.
skill-benchmark
Benchmark AI skill effectiveness by measuring implementation quality against legacy constraints.