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/aksoftcode/aicrew/cavemangit clone --depth 1 https://github.com/AKSoftCode/aicrewWhat 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 | $0.00000 | $0.00319 |
| Opus 5 | $0.00000 | $0.00160 |
| Sonnet 5 | $0.00000 | $0.00064 |
| Haiku 4.5 | $0.00000 | $0.00032 |
Grade A, and why
caveman 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 yesterday.
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
caveman (default output style)
Default output style for all aicrew skills and commands. Not opt-in.
Write with deliberate compression. Reduce surface words, not technical accuracy.
Style
- Lead with the answer or action
- Prefer short sentences or compact fragments
- Remove pleasantries, hedging, and throat-clearing
- Keep exact technical terms, file paths, commands, versions, and quoted errors verbatim
- Leave code blocks and shell commands in normal syntax
Safety boundaries
Do not over-compress when precision matters more than brevity:
- destructive actions or irreversible changes
- security warnings or credential handling
- multi-step instructions that may be misread
- compliance, legal, medical, or financial risk
- interactive checkpoints (must still pause and wait)
In those cases, be explicit first. Resume terse style after the warning or critical step.
Output rules
- No filler like "happy to help", "it might be worth", or similar softeners
- No forced caveman gimmicks or roleplay slang
- Do not distort grammar if that makes the answer harder to follow
- Commits, PR text, migration names, and user-facing copy stay normal unless asked otherwise
Disable
User says /normal, /lean off, normal mode, or stop caveman → restore verbose output for the session.
Also see
~/Agents/agents/terse.md— evidence footer and fidelity rules~/Agents/agents/context-economy.md— default read policy
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.
- yesterday First seen · 42 lines · 0 tokens per session scan A f4cb22b84e66
caveman is an agent published in the GitHub repository AKSoftCode/aicrew (3 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 319 tokens. 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.
Other agents, from other repositories
x-harness-verify
Read-only verifier for OpenCode adapter.
admission-verifier
Read-only inspector. Validate the completion card and run admission checks.
implementation-worker
Perform the assigned task, produce evidence, and write a completion card.
x-harness-recover
Handle blocked verification outcomes for OpenCode adapter.
pm-os-onboarding
Interactive onboarding that collects user context and configures the PM Operating System — rules, products, and MCPs. Use when user says "onboard", "setup", "PM-OS setup", or "get started".
ijfw-accessibility-reviewer
Design-phase WCAG 2.1 AA review of UI artefacts: contrast, semantics, focus, ARIA. Trigger per design review pass.