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 commands/juliusbrussee/caveman-code/goalgit 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 | $0.00019 | $0.00302 |
| Opus 5 | $0.00010 | $0.00151 |
| Sonnet 5 | $0.00004 | $0.00060 |
| Haiku 4.5 | $0.00002 | $0.00030 |
Grade A, and why
goal 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 3d 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
Launching an autonomous goal loop for: $ARGUMENTS
The driver runs in a separate background process: spawning fresh caveman -p per iteration, persisting state at <cwd>/.cave/goal/<id>/. Termination on completion sentinel <goal-complete/>, iteration cap (default 50), wall-clock cap (24h), $ cap ($10), or 5 consecutive iterations w/o repo change.
Driver launched in background:
!mkdir -p .cave/goal/_logs && nohup caveman goal start "$ARGUMENTS" --quiet > .cave/goal/_logs/$(date +%Y%m%d%H%M%S).log 2>&1 & disown ; echo "driver pid=$! log=.cave/goal/_logs/"
Tell the user:
- the goal id (find it with
caveman goal list) - check progress with
caveman goal statusor tail the log file printed above - cancel with
caveman goal cancel - the GOAL.md file under
.cave/goal/<id>/can be edited mid-run; the next iteration re-reads it
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.
- 3d ago First seen · 24 lines · 19 tokens per session scan A 4098f830756c
goal is a command published in the GitHub repository JuliusBrussee/caveman-code (929 stars, last pushed 19d ago), licensed MIT. It adds 19 tokens to every session and 302 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 commands, from other repositories
minutes-ideas
Surface recent voice memos and ideas captured from any device. Use when the user asks "what ideas did I have?", "what were my recent memos?", "what did I record while walking?", or wants to recall a captured thought.
autobot-result
Print the most recent result.md for an autobot session, so the user can see how a bot is doing without attaching to its tmux session.
engage.actions
Execute Phase 7 - Actions on Objectives and Goal Achievement.
version
Show installed vs latest ai-sdlc plugin version. Bypasses the 24h SessionStart cache.
thread
Manage conversation threads (create, switch, update, delete, show).
handoff
Generate or load a session handoff. Usage: /handoff [create|resume].