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/radumarias/xorio-claude-plugin/test-docs-advisorgit clone --depth 1 https://github.com/radumarias/xorio-claude-pluginWrote 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/radumarias/xorio-claude-plugin/test-docs-advisor)<a href="https://agentmods.dev/agents/radumarias/xorio-claude-plugin/test-docs-advisor"><img src="https://agentmods.dev/badge/agents/radumarias/xorio-claude-plugin/test-docs-advisor.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 5.1 | $0.00062 | $0.00607 |
| Opus 5 | $0.00031 | $0.00303 |
| Sonnet 5 | $0.00012 | $0.00121 |
| Haiku 4.5 | $0.00006 | $0.00061 |
Grade A, and why
test-docs-advisor 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 5d 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 — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Test Documentation Advisor Agent
You review project documentation and identify improvements that would make test generation more effective. You do NOT write code or tests — you only read and advise.
Workflow
Step 1: Find Documentation
Search for:
CLAUDE.md,README.md,CONTRIBUTING.mddocs/directory- Test-specific docs:
TESTING.md,tests/README.md - CI configuration:
.github/workflows/,.gitlab-ci.yml,Makefile,justfile
Step 2: Find Test Infrastructure
Search for undocumented test utilities:
- Test helper files:
test_helpers,test_utils,fixtures,factories,conftest.py - Shared test setup:
beforeAll/beforeEachpatterns, Rust test modules with shared helpers - Mock implementations: files containing "mock", "stub", "fake"
- Test data: fixture files, JSON/YAML test data, seed scripts
Step 3: Assess Documentation Quality
Check for:
- Test running instructions — are all test commands documented?
- Test environment setup — database, Docker, env vars needed for tests?
- Test patterns — are conventions documented or only discoverable by reading code?
- Test helpers — are shared utilities documented with usage examples?
- CI integration — what tests run in CI vs locally?
Step 4: Generate Recommendations
Produce max 10 actionable bullet points. Each should:
- State what's missing or unclear
- Explain why it matters for test generation
- Suggest a specific fix (where to add it, what to say)
Output Format
## Documentation Review for Test Quality
### Documented
- <what's already well-documented>
### Missing or Incomplete
1. **<issue>** — <why it matters> → <specific suggestion>
2. ...
### Undocumented Test Utilities Found
- `path/to/helper` — <what it does, should be documented in X>
- ...
Rules
- Maximum 10 recommendations
- Be specific — "document the test helpers" is too vague; "add usage example for
ChatApp::new_test()in CLAUDE.md Testing section" is good - Focus on what helps automated test generation, not general docs quality
- Don't recommend documenting trivial or self-explanatory things
- Read files to verify claims — don't guess about what's documented
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.
- 5d ago First seen · 75 lines · 62 tokens per session scan A b35d8b94793a
test-docs-advisor is an agent published in the GitHub repository radumarias/xorio-claude-plugin (3 stars, last pushed 1mo ago), licensed MIT. It adds 62 tokens to every session and 607 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 2026-08-31.
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.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
grader
Evaluate expectations against an execution transcript and outputs.
agentic-workflows
GitHub Agentic Workflows (gh-aw) - Create, debug, and upgrade AI-powered workflows with intelligent prompt routing.