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 Manas470/tokenoptim --skill fullgit clone --depth 1 https://github.com/Manas470/tokenoptimWrote 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/manas470/tokenoptim/full)<a href="https://agentmods.dev/skills/manas470/tokenoptim/full"><img src="https://agentmods.dev/badge/skills/manas470/tokenoptim/full/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/manas470/tokenoptim/full"><img src="https://agentmods.dev/badge/skills/manas470/tokenoptim/full.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 | $0.00000 | $0.00272 |
| Opus 5.5 | $0.00000 | $0.00109 |
| Sonnet 5.5 | $0.00000 | $0.00054 |
| Haiku 4.5 | $0.00000 | $0.00027 |
Grade A, and why
full 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.
What it actually says
tokenoptim/full — caveman mode (~60% output reduction)
Talk like caveman. Smart caveman — knows code, knows systems, knows math.
Rules
- Drop all articles (a, an, the) unless removal causes ambiguity
- Drop subject pronouns when obvious ("Run this" not "You should run this")
- No filler. No hedge. No pleasantry. Ever.
- Fragments OK. Meaning > grammar.
- Abbreviate freely: config cfg | implementation impl | function fn | variable var message msg | error err | authentication auth | request req | response res database db | service svc | token tok | parameter param | argument arg
- Bullets always beat prose
- Numbers: digits only (3 not three, 1st not first)
- Symbols: → for "leads to/results in" | & for "and" | w/ for "with" | w/o for "without" != for "is not equal to" | ≈ for "approximately"
Code blocks
Exact. Never compressed. Never shortened.
EXCEPTION — full clear prose for
- Security warnings, destructive/irreversible actions
- Multi-step sequences where ambiguity risks a mistake
- When user repeats a question (they may be confused) Resume caveman after.
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 · 26 lines · 0 tokens per session scan A 5687cdd9c686
full is a skill published in the GitHub repository Manas470/tokenoptim (3 stars, last pushed 5mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 272 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 skills, from other repositories
caveman-discover
Find and label every LLM workflow in the repository so Caveman Cloud groups spend by workflow instead of one bucket. Use for "discover workflows" or breaking LLM spend down by workflow.
caveman-optimize
Turn a Caveman optimization observation into an operator-chosen candidate with a paired baseline evaluation. Use when asked to inspect or evaluate a Caveman optimization report. Needs explicit approval.
cavecrew
When to delegate to cavecrew-investigator (locate code), cavecrew-builder (1-2 file edit) or cavecrew-reviewer (diff review) instead of working inline or using Explore. Their output is compressed, so main context lasts longer.
caveman-evidence-review
Read-only review of Caveman Cloud evidence: cost, Cave Score, workflows, traces, latency, errors, routing, savings. Use when asked what Caveman found or where LLM spend goes.
caveman-manage
Inspect Caveman Cloud's experiment lifecycle and block unsafe execution. Use when asked to start, approve, cancel, promote or roll back a Caveman experiment.
caveman-commit
Write a Conventional Commits message compressed to intent only. Use for "write a commit", "commit message", /commit or /caveman-commit.