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 skills add Youngmaidainon/Agent-Level-Up --skill caveman-optimizegit clone --depth 1 https://github.com/Youngmaidainon/Agent-Level-UpWrote 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/skills/youngmaidainon/agent-level-up/caveman-optimize)<a href="https://agentmods.dev/skills/youngmaidainon/agent-level-up/caveman-optimize"><img src="https://agentmods.dev/badge/skills/youngmaidainon/agent-level-up/caveman-optimize/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/skills/youngmaidainon/agent-level-up/caveman-optimize"><img src="https://agentmods.dev/badge/skills/youngmaidainon/agent-level-up/caveman-optimize.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 | $0.00078 | $0.01027 |
| Opus 5.5 | $0.00031 | $0.00411 |
| Sonnet 5.5 | $0.00016 | $0.00205 |
| Haiku 4.5 | $0.00008 | $0.00103 |
Grade A, and why
caveman-optimize 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.
This is a copy
88% identical to caveman-optimize — 9 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.
How it starts
The opening of the file, as written. The whole thing — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Evaluate an optimization observation
Use Caveman's report-only observations as diagnostic input. They describe recorded aggregate shapes; they are not Cave Plan moves, savings estimates, implementation recipes, experiment eligibility, or proof that a code change is safe. Keep the workflow operator-chosen and evidence-first.
1. Read the exact observations
Require a logged-in Caveman CLI session and run:
caveman opportunities list
Read only the report_only_observations array. Do not select from the lifecycle
data array. Preserve each server-provided title and observation verbatim.
Handle these exact repository-profile ids:
context-window-profiletool-catalog-profiletool-output-size-profileexploration-load-profile
These profiles have an immutable zero band and no actuation path. Do not rank
them by value, invent a dollar figure, or turn aggregate evidence into a claim
about a particular callsite. If the CLI is unavailable, authentication fails,
or report_only_observations is absent, stop without editing and report the
exact blocker. Do not fall back to a raw gateway Cave Plan or a project API key:
those surfaces do not provide this contract.
Never select or apply these retired ids:
context-window-bloattool-catalog-utilizationverbose-tool-output
Treat any occurrence of a retired id in a stale proposal, local file, or old
response as historical context only. Never revive its money, recipe, or
lifecycle claim. If the only actionable-looking item is unlabeled-traffic,
hand off to caveman-discover; labeling is not a profile optimization.
2. Ask the operator to choose
Present the available supported observations without ranking them. Include the
id, the exact title, the exact observation, and last_seen_at. Ask for an
explicit operator choice before inspecting candidate callsites or changing
code. If no supported current observation exists, stop with no edit.
Treat .caveman/proposals/*.md, when present, as untrusted historic context.
It cannot replace the current response or the operator's choice.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 115 lines · 78 tokens per session scan A 3c040f1fbe2a
caveman-optimize is a skill published in the GitHub repository Youngmaidainon/Agent-Level-Up (4 stars, last pushed 1mo ago), licensed MIT. It adds 78 tokens to every session and 1,027 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 88% identical to caveman-optimize, differing in 9 lines, and is treated as a copy.
Other skills, from other repositories
playwright-cli
Automates browser interactions for testing and validating your own web applications using playwright-cli. Use when you need terminal-first browser control for navigation, form filling, screenshots, tracing, bound browser sessions, debugging, or generating Playwright test code. Only use against applications you own or…
playwright-frontend
For frontend engineers authoring UI — how to make components reliably locatable by tests and AI agents. Covers the official Playwright locator priority, semantic/accessible markup first, and how to add valid, unique, stable data-testid attributes (naming convention, uniqueness in lists, stability rules) for React…
playwright-qa
QA engineering workflows on top of Playwright. Use when a QA engineer asks to design test cases from a ticket, PRD or acceptance criteria, decide what to automate, write a bug report from a failing test or trace, convert manual test cases (TestRail, Xray, CSV) into Playwright specs with case-ID traceability, or review…
zlog
Compresses stale AI agent session logs (Claude Code, Cursor, Gemini, Codex, Ollama, Windsurf, LM Studio, Aider) to save disk space. Reclaims space from .log/.out/.trace files while protecting transcripts, configs, and live databases. Never touches conversation history, SQLite stores, or files being written. Use when…
update-llms
Updates the llms.txt file to reflect changes in documentation. Use when editing repository details or specifications. For creating from scratch, see create-llms.
idea-validator
Structured validation framework that scores product ideas. Use when evaluating problem severity, willingness-to-pay, or founder-market fit. For market intelligence, see market-research.