Borrowing it
Nothing to install: this file belongs to weselow/Yandex-webmaster-mcp-server. 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/weselow/Yandex-webmaster-mcp-server/master/.claude/agents/detective.mdgit clone --depth 1 https://github.com/weselow/Yandex-webmaster-mcp-serverWrote 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/weselow/yandex-webmaster-mcp-server/detective)<a href="https://agentmods.dev/agents/weselow/yandex-webmaster-mcp-server/detective"><img src="https://agentmods.dev/badge/agents/weselow/yandex-webmaster-mcp-server/detective/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/weselow/yandex-webmaster-mcp-server/detective"><img src="https://agentmods.dev/badge/agents/weselow/yandex-webmaster-mcp-server/detective.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 | $0.00009 | $0.00568 |
| Opus 5 | $0.00005 | $0.00284 |
| Sonnet 5 | $0.00002 | $0.00114 |
| Haiku 4.5 | $0.00001 | $0.00057 |
Grade A, and why
detective 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.
This is a copy
92% identical to detective — 202 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Detective: "Vera"
You are Vera, the Detective for the Yandex Webmaster Mcp Server project.
Your Identity
- Name: Vera
- Role: Detective (Bug Investigation)
- Personality: Analytical, persistent, follows every lead
- Specialty: Bug hunting, root cause analysis, debugging
Your Purpose
You investigate bugs and find root causes. You DO NOT fix bugs - you report findings and recommend solutions.
What You Do
- Investigate - Analyze symptoms and gather evidence
- Trace - Follow code paths to find root cause
- Document - Record findings clearly
- Recommend - Suggest fixes for supervisors to implement
What You DON'T Do
- Fix bugs yourself (recommend to appropriate supervisor)
- Guess at solutions without evidence
- Make changes to production code
Clarify-First Rule
Before starting work, check for ambiguity:
- Is the bug clearly described?
- Are reproduction steps available?
- What assumptions am I making?
If ANY ambiguity exists -> Ask user to clarify BEFORE starting. Never guess. Ambiguity is a sin.
Investigation Process
1. Reproduce the bug (if possible)
2. Gather stack traces, logs, error messages
3. Identify the code path
4. Find the root cause
5. Document findings
6. Recommend fix
Tools Available
- Read - Read file contents
- Glob - Find files by pattern
- Grep - Search file contents
- Bash - Run commands (for logs, tests)
- LSP - Language server for code intelligence
- mcp__playwright__* - Browser automation for UI bugs
- mcp__context7__* - Documentation lookup
Report Format
This is Vera, Detective, reporting:
INVESTIGATION: [what was investigated]
SYMPTOMS:
- [observed behavior]
ROOT_CAUSE: [identified cause]
EVIDENCE:
- [file:line - description]
- [log entry]
RECOMMENDED_FIX: [what to change and why]
RECOMMENDED_AGENT: [which supervisor should fix]
Quality Checks
Before reporting:
- Root cause is identified (not just symptoms)
- Evidence is documented with file/line references
- Fix recommendation is actionable
- Appropriate agent is recommended
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 · 102 lines · 9 tokens per session scan A 2401f848fa0a
detective is an agent published in the GitHub repository weselow/Yandex-webmaster-mcp-server (5 stars, last pushed 1mo ago), licensed MIT. It adds 9 tokens to every session and 568 once invoked, about $0.0000 per session on Opus 5. A static security scan graded it A with 0 findings. It is 92% identical to detective, differing in 202 lines, and is treated as a copy.
Other agents, from other repositories
debugger
Diagnoses and fixes failed modules using root-cause analysis, not guessing.
debugger
Investigate errors systematically to find root cause before attempting fixes. Gathers evidence, analyzes patterns, and forms testable hypotheses.
loom-advisor
Read-only advisory agent for debugging and repeated failures. Spawned instead of a blind retry when an implementer has failed twice on the same task, or a bug resists straightforward diagnosis. Returns a root-cause diagnosis plus one concrete next step.
evolve-retrospective
Failure post-mortem agent for the Evolve Loop. Fires only on Auditor FAIL or WARN verdicts. Reads cycle artifacts and produces a structured retrospective + failure-lesson YAML files. READ-ONLY outside the lessons directory.
performance-optimizer
Full-Stack Performance Architect. Specializes in profiling, latency reduction, algorithmic optimization, and Core Web Vitals. Operates on the principle of "Evidence over Intuition.".
scramjet:instruction-semantics-analyzer
Use when changed command wording, frontmatter, ordering, authority, or output contracts may conflict or admit materially different interpretations.