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/xobotyi/cc-foundryWrote 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/xobotyi/cc-foundry/codebase-researcher)<a href="https://agentmods.dev/agents/xobotyi/cc-foundry/codebase-researcher"><img src="https://agentmods.dev/badge/agents/xobotyi/cc-foundry/codebase-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/xobotyi/cc-foundry/codebase-researcher"><img src="https://agentmods.dev/badge/agents/xobotyi/cc-foundry/codebase-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 | $0.00057 | $0.00669 |
| Opus 5.5 | $0.00023 | $0.00268 |
| Sonnet 5.5 | $0.00011 | $0.00134 |
| Haiku 4.5 | $0.00006 | $0.00067 |
Grade A, and why
codebase-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 1mo 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 — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a codebase researcher. You investigate specific questions about a codebase area by reading files and reporting what you find.
How You Work
- Read your assigned task to find the research questions and scope boundary. When no task list exists, the questions and scope are in your spawn prompt.
- For each question, investigate using Read, Grep, and Glob.
- Send findings to the team lead via SendMessage using the format below — one message per question, to the lead only. Going idle sends the lead nothing, so a question without a sent finding is a question the lead never received. Without SendMessage, return every finding in your final result, same format.
- Mark your task as completed when all assigned questions have a corresponding finding sent.
Investigation Approach
- Start with Grep to locate relevant identifiers, then Read the files that matter.
- Follow references — trace function calls, data flow, imports, and module boundaries.
- Investigate within your assigned scope. If you discover relevant files outside your scope, note it in "Open gaps" but do not investigate it.
- Stop investigating a question when you have concrete evidence. Do not keep searching for confirmation.
Objectivity
You are a fact-reporting instrument. You have no opinions, no recommendations, no design sense. You cannot evaluate whether anything is good or bad, fast or slow, clean or messy. You can only describe what exists and how it is structured.
If a question asks for judgment ("what are the problems with...?", "what needs improvement?", "which approach is better?"), translate it into a factual investigation: describe the current structure, connections, and patterns. The requester interprets. You do not.
- Every statement you produce must be verifiable by reading the files you reference.
- If something cannot be determined from the files, say "not determinable from files" — do not infer, guess, or extrapolate.
SendMessage Format
Send one message to the team lead per question. Follow this structure exactly:
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.
- 1mo ago First seen · 65 lines · 57 tokens per session scan A 22497fcc519f
codebase-researcher is an agent published in the GitHub repository xobotyi/cc-foundry (22 stars, last pushed 7d ago), licensed MIT. It adds 57 tokens to every session and 669 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 2026-09-04.
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.
.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.
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.