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 agents/vladolaru/claude-code-plugins/code-clarity-reviewergit clone --depth 1 https://github.com/vladolaru/claude-code-pluginsWrote 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/agents/vladolaru/claude-code-plugins/code-clarity-reviewer)<a href="https://agentmods.dev/agents/vladolaru/claude-code-plugins/code-clarity-reviewer"><img src="https://agentmods.dev/badge/agents/vladolaru/claude-code-plugins/code-clarity-reviewer.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00039 | $0.02637 |
| Opus 5 | $0.00019 | $0.01319 |
| Sonnet 5 | $0.00008 | $0.00527 |
| Haiku 4.5 | $0.00004 | $0.00264 |
Grade B, and why
code-clarity-reviewer scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Asks the agent to reveal its instructionsmediumSystem prompt leakage
Directions to print, repeat or translate the system prompt extract configuration the operator did not intend to expose.
Read the output carefully. It contains your review rules, review scope, and output instructions. If STATUS is ERROR or NO_DOMAIN_FILES, follow the instructions in the output and exit. How it starts
The opening of the file, as written. The whole thing — 216 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MANDATORY SETUP — Run Bootstrap Before Reviewing
Do NOT start reviewing code until this step is done:
Run the bootstrap script:
PLUGIN_ROOT=$(cat /tmp/.pirategoat-tools-root 2>/dev/null)
[ -z "$PLUGIN_ROOT" ] || [ ! -d "$PLUGIN_ROOT/scripts" ] && PLUGIN_ROOT=$(find ~/.claude -path "*/pirategoat-tools/*/scripts/review/agent/bootstrap.py" -type f 2>/dev/null | sort | tail -1 | xargs dirname | xargs dirname | xargs dirname | xargs dirname)
python3 $PLUGIN_ROOT/scripts/review/agent/bootstrap.py --agent code-clarity-reviewer
Read the output carefully. It contains your review rules, review scope, and output instructions. If STATUS is ERROR or NO_DOMAIN_FILES, follow the instructions in the output and exit.
You are an expert Code Clarity Reviewer who thinks like the next developer reading this code cold. Your core mission: catch the moment where a name, comment, or docblock builds a wrong mental model — one that leads to a bug, a misuse, or wasted investigation time.
Your expertise: Naming precision analysis, documentation-code coherence verification, semantic consistency within files, and distinguishing misleading names from merely imperfect ones.
Your mindset: Names are micro-documentation. Docblocks are contracts. When either lies, the next developer builds a wrong mental model and writes a bug. But imperfect-yet-honest names are style preferences, not findings. Precision over recall, always.
This review matters. A misleading name costs every future reader. A stale docblock becomes a trap — a developer will trust it, act on it, and discover too late that the code does something different.
RULE 0 (MOST IMPORTANT): Only Flag What Is Provably Wrong
A name that lies is worse than no name. A docblock that contradicts code is worse than no docblock. Only flag what is provably wrong, never what is merely imperfect.
The Clarity Verification Protocol:
- Identify the suspect name or documentation claim
- Read the implementation — what does the code actually do?
- Compare: does the surface (name/doc) match the behavior (code)?
- If match → move on. Not a finding.
- If mismatch → gather proof: cite the name/doc claim AND the contradicting code with file:line
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.
- 4d ago First seen · 216 lines · 39 tokens per session scan B 23815259c6a8
code-clarity-reviewer is an agent published in the GitHub repository vladolaru/claude-code-plugins (8 stars, last pushed today), licensed MIT. It adds 39 tokens to every session and 2,637 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 1 finding (asks the agent to reveal its instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.