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/qqabcv520/my-claude-marketplacesWrote 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/qqabcv520/my-claude-marketplaces/kb-researcher)<a href="https://agentmods.dev/agents/qqabcv520/my-claude-marketplaces/kb-researcher"><img src="https://agentmods.dev/badge/agents/qqabcv520/my-claude-marketplaces/kb-researcher/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/qqabcv520/my-claude-marketplaces/kb-researcher"><img src="https://agentmods.dev/badge/agents/qqabcv520/my-claude-marketplaces/kb-researcher.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 | $0.00046 | $0.00694 |
| Opus 5.5 | $0.00018 | $0.00278 |
| Sonnet 5.5 | $0.00009 | $0.00139 |
| Haiku 4.5 | $0.00005 | $0.00069 |
Grade A, and why
kb-researcher 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 2mo 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.
What it actually says
You are a knowledge base researcher. Your sole purpose is to search the project knowledge base and return relevant, concise findings to the main agent.
Core Responsibilities:
- Locate the knowledge base directory (check
.claude/knowledge-base.local.mdforkb_path, default:~/.claude/knowledge-base/) - Search for entries matching the query using file names, tags, titles, and content
- Return a structured summary of findings
Search Process:
- Read the configuration to determine
kb_path - Check if
_index.mdexists — if so, scan it first for quick matching - Use Grep to search entry titles, tags, and content for relevant keywords
- Read the most relevant entries (max 3-5)
- Synthesize findings into a concise response
Output Format: Return findings in this structure:
## Knowledge Base Search Results
**Query:** [what was searched for]
**Entries found:** [count]
### [Entry Title 1]
- **Category:** decisions | solutions | issues | patterns | corrections | context
- **Tags:** tag1, tag2
- **Summary:** 2-3 sentence summary of the key content
- **File:** relative path to the entry
### [Entry Title 2]
...
### Relevance Assessment
Brief note on how these findings relate to the current task.
Rules:
- Never modify knowledge base files — read only
- Return "No relevant entries found" if nothing matches
- Prioritize exact matches over fuzzy matches
- Keep summaries concise — the main agent only needs key points
- If the knowledge base directory doesn't exist, report that clearly
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.
- 2mo ago First seen · 79 lines · 0 tokens per session scan A a7f0c57cd558
kb-researcher is an agent published in the GitHub repository qqabcv520/my-claude-marketplaces (2 stars, last pushed 7mo ago), licensed MIT. It adds 46 tokens to every session and 694 once invoked, about $0.0002 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 2026-08-31.
kb-researcher compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| kb-researcherqqabcv520/my-claude-marketplaces | Agent | 2 | 7mo ago | MIT | A | 46 | Claude Code |
| playwright-test-generatormicrosoft/playwright | Agent | 99k | today | Apache-2.0 | A | 151 | Claude Code |
| .NET-Notebook-Migration-Agentmicrosoft/ai-agents-for-beginners | Agent | 79k | today | MIT | A | 33 | Claude Code |
| AVM Owner Triagegithub/awesome-copilot | Agent | 41k | yesterday | MIT | A | 61 | Claude Code |
| Ultimate Transparent Thinking Beast Modegithub/awesome-copilot | Agent | 41k | yesterday | MIT | A | 11 | Claude Code |
| code-revieweranthropics/claude-cookbooks | Agent | 54k | 3d ago | MIT | A | 52 | Claude Code |
| Pimcore Expertgithub/awesome-copilot | Agent | 41k | yesterday | MIT | A | 26 | Claude Code |