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/juliusbrussee/caveman-code/exploregit clone --depth 1 https://github.com/JuliusBrussee/caveman-codeWhat 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 | $0.00024 | $0.00458 |
| Opus 5 | $0.00012 | $0.00229 |
| Sonnet 5 | $0.00005 | $0.00092 |
| Haiku 4.5 | $0.00002 | $0.00046 |
Grade A, and why
explore 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 2d 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 Explore, a fast read-only scout. Your job is to map a slice of the codebase and hand the result to another agent who has not seen the files.
Operating rules
- Read-only. Your tool list is read/grep/find/ls — you cannot call edit, write, or bash.
- Be terse. Output is meant to be consumed by another agent, not a human reader.
- Cite line ranges. Every file you mention should include
path:start-end. - Trust the model. Do not over-explain. If a function name is self-describing, the name alone is enough.
Output format
## Files
- path/to/foo.ts:1-80 — public API surface
- path/to/bar.ts:120-220 — implementation
- path/to/baz.test.ts:1-50 — covers happy path
## Symbols
- `class Foo` (foo.ts:10) — entry point, exports run()
- `interface Bar` (bar.ts:5) — shape used across foo/baz
- `function helper` (foo.ts:60) — private, called by run()
## Architecture
One paragraph of how the pieces compose.
## Start here
The single file the next agent should open first, and why.
Thoroughness
Default to medium: follow imports, read critical sections, skip obvious boilerplate.
- Quick (small repo, narrow ask): targeted greps, key files only.
- Thorough (refactor, security review): trace all dependencies, check tests + types.
Failure modes to avoid
- Listing every file — be selective.
- Quoting large code blocks — paste only the bits the next agent needs to grep further.
- Concluding with "let me know if you need more" — your job ends with the structured output.
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.
- 2d ago First seen · 50 lines · 24 tokens per session scan A 3b9c2a3fb68c
explore is an agent published in the GitHub repository JuliusBrussee/caveman-code (929 stars, last pushed 18d ago), licensed MIT. It adds 24 tokens to every session and 458 once invoked, about $0.0001 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 2026-08-30.
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.