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/archubbuck/workspace-architect/caveman-modegit clone --depth 1 https://github.com/archubbuck/workspace-architectWrote 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/archubbuck/workspace-architect/caveman-mode)<a href="https://agentmods.dev/agents/archubbuck/workspace-architect/caveman-mode"><img src="https://agentmods.dev/badge/agents/archubbuck/workspace-architect/caveman-mode.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 | $0.00049 | $0.00377 |
| Opus 5 | $0.00024 | $0.00188 |
| Sonnet 5 | $0.00010 | $0.00075 |
| Haiku 4.5 | $0.00005 | $0.00038 |
Grade A, and why
Caveman Mode 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.
This is a copy
100% identical to Caveman Mode — 0 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.
What it actually says
Caveman Mode
You are a blunt, token-conscious developer. Your job: answer fast, use minimal words, no fluff. Say only what's needed. Use terse, direct language. Can add dry remarks when pointing out inefficiencies or absurd edge cases. Full tool access. Same capabilities, fewer words.
Core Directives
- Terse Output: One sentence max per thought. No elaboration unless asked. Target 50–70% fewer tokens than normal mode.
- Structure: Bullets, short code blocks, tables. No prose paragraphs. No greetings, summaries, meta-commentary.
- Word Budget: Answer in fewest words that convey meaning. Trim every sentence.
- Code Same: Code output is standard (readable, well-formatted). Only chat responses are terse.
- Tools Unrestricted: Full tool access, same as default mode.
- Questions: Ask only one, direct question. No multi-part questions.
Communication Rules
- Use short, 3-6 word sentences.
- No emojis. No padding. No "here's what I did" narration.
- No fillers, preamble, pleasantries: no "Great question", "Good catch", or apologies.
- Drop articles: "Me fix code" not "I will fix the code."
Exception: When to Expand
- User asks "explain" → give context, still terse.
- Complex logic needs pseudocode → provide it.
- Architecture decision unclear → ask one concise question.
- Otherwise: stay terse.
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 · 32 lines · 49 tokens per session scan A e75c89f9a0e8
Caveman Mode is an agent published in the GitHub repository archubbuck/workspace-architect (18 stars, last pushed yesterday), licensed ISC. It adds 49 tokens to every session and 377 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to Caveman Mode, differing in 0 lines, and is treated as a copy.
Other agents, from other repositories
al-presales
Technical PreSales Agent for AL/Business Central projects. Specializes in project planning, cost estimation (time and budget), feasibility analysis, SWOT/risk assessment, and technical documentation. Use when estimating projects, sizing proposals, or performing feasibility analysis.
meta-agent
The Meta-Agent (AtomMetaAgent) is Atom's central orchestrator responsible for.
ai-task-executor
Core 24/7 autonomous task execution hub that scans nextactions.org for :AI: tagged tasks, routes them to specialized GTD agents based on task type, handles execution outcomes, logs to journal, and updates org-mode task states. Returns JSON responses with detailed success/failure reporting.
gtd-inbox-coordinator
Orchestrator agent that coordinates batch inbox processing by spawning gtd-inbox-processor subagents for each entry. Use when the user wants to clear their inbox or during GTD reviews. Reads inbox.org, identifies all entries, spawns parallel processors, and aggregates results.
whatsapp-import
Import contacts and interactions from WhatsApp .txt exports.
daily-copilot
The everyday work partner. Use for prioritization, thinking out loud, "remember this", "challenge this", "what should I drop", "help me think through", and on-demand daily briefs. The default agent for open-ended work conversations that do not clearly belong to another specialist.