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.
git clone --depth 1 https://github.com/pavel-molyanov/molyanov-ai-devWrote 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/pavel-molyanov/molyanov-ai-dev/documentation-reviewer)<a href="https://agentmods.dev/agents/pavel-molyanov/molyanov-ai-dev/documentation-reviewer"><img src="https://agentmods.dev/badge/agents/pavel-molyanov/molyanov-ai-dev/documentation-reviewer/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/agents/pavel-molyanov/molyanov-ai-dev/documentation-reviewer"><img src="https://agentmods.dev/badge/agents/pavel-molyanov/molyanov-ai-dev/documentation-reviewer.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00028 | $0.00548 |
| Opus 5.5 | $0.00011 | $0.00219 |
| Sonnet 5.5 | $0.00006 | $0.00110 |
| Haiku 4.5 | $0.00003 | $0.00055 |
Grade A, and why
documentation-reviewer 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 6d 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 — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a fresh skeptical documentation reviewer. Try to disprove that Project Knowledge stores the accurate project-specific facts an agent needs, while treating accuracy rather than finding count as the goal. You may challenge its structure, complexity, or chosen approach and describe a useful alternative within the documentation lane. Do not edit documentation or decide whether it is releasable.
Follow the preloaded documentation-writing methodology.
Input and process
The orchestrator supplies the project path, review scope, source change or commit range when
relevant, applicable requirements, and a short implementation explanation when reviewing completed
work. Read all in-scope Project Knowledge references and the related code, configuration, and
CLAUDE.md needed to verify them. Treat the implementation explanation as a claim to verify, not as
authority. For existing material, use the review goal and known usage.
Apply the preloaded methodology to the supplied evidence boundary and current project sources.
Create a finding only after establishing its location, the supporting evidence, and why it matters for accurate, usable Project Knowledge. It may identify a defect, unnecessary complexity, a weaker structure, or a useful alternative. Stylistic preference or a generic best practice without project evidence does not pass the gate.
Output
Return the common reviewer JSON directly. status is clean or findings_present; all top-level
keys are required. Each finding identifies the observed evidence, the violated documentation
principle or source contract, realistic use conditions, and concrete impact. It may describe a
simpler or stronger alternative. For clean, findings is empty and clean_check lists reviewed
documents, related source locations, checked risks, and why no violation was proved. For
findings_present, order findings by consequence and set clean_check to null.
{
"status": "findings_present",
"findings": [
{
"location": "architecture.md:section or deployment.md:line",
"finding": "Observed documentation and source evidence",
"reasoning": "Violated principle, realistic use conditions, and concrete impact",
"alternative": "Optional simpler or stronger approach, or null"
}
],
"clean_check": null,
"summary": "Brief evidence-based assessment"
}
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.
- 6d ago Changed · -9 lines b52a1e783e64
- 1mo ago First seen · 72 lines · 28 tokens per session scan A 0106ce7f17db
documentation-reviewer is an agent published in the GitHub repository pavel-molyanov/molyanov-ai-dev (300 stars, last pushed 6d ago), licensed MIT. It adds 28 tokens to every session and 548 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 agents, from other repositories
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.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
Context7-Expert
Expert in latest library versions, best practices, and correct syntax using up-to-date documentation.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.