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.
git clone --depth 1 https://github.com/alexgreensh/token-optimizerWrote 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/commands/alexgreensh/token-optimizer/health)<a href="https://agentmods.dev/commands/alexgreensh/token-optimizer/health"><img src="https://agentmods.dev/badge/commands/alexgreensh/token-optimizer/health/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/commands/alexgreensh/token-optimizer/health"><img src="https://agentmods.dev/badge/commands/alexgreensh/token-optimizer/health.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 | $0.00017 | $0.01464 |
| Opus 5 | $0.00009 | $0.00732 |
| Sonnet 5 | $0.00003 | $0.00293 |
| Haiku 4.5 | $0.00002 | $0.00146 |
Grade C, and why
health scanned grade C with 2 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
$(find -L "$HOME/.claude/skills" "$HOME/.claude/plugins/cache" "$HOME/.claude/token-optimizer" "$HOME/.codex/skills" "$HOME/.codex/plugins/cache" "$HOME/.config/opencode/plugins/cache" "$HOME/.config/opencode/plugins" -t Enumerates other installed skillsmediumAgent snooping
Other skills' SKILL.md files reveal prompts, capabilities and secrets that should be invisible to peers.
$(find -L "$HOME/.claude/skills" "$HOME/.claude/plugins/cache" "$HOME/.claude/token-optimizer" "$HOME/.codex/skills" "$HOME/.codex/plugins/cache" "$HOME/.config/opencode/plugins/cache" "$HOME/.config/opencode/plugins" -t The source is not reproduced here
A licence we could not identify
The repository carries a LICENSE file, but it is custom or dual enough that GitHub cannot name it and neither can this catalogue. Unknown terms are not permission, so the body is not copied here. Read the licence at the source and decide for yourself.
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 Changed ab3bdd599917
- 9d ago First seen · 82 lines · 17 tokens per session scan C 22615fd33341
health is a command published in the GitHub repository alexgreensh/token-optimizer (2,199 stars, last pushed yesterday), with no licence file. It adds 17 tokens to every session and 1,464 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it C with 2 findings (reads agent configuration directories, enumerates other installed skills). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other commands, from other repositories
eval-merge
Use the Read tool to load .skill-compass/{skill-name}/manifest.json. Verify.
enum-udp
UDP scan + service follow-up — top ports first, full sweep only when justified.
kerberos
Kerberos attacks — AS-REP roasting and Kerberoasting.
resolve-conflict
Systematic merge conflict resolution with context analysis.
check
Run TYPO3 conformance check on current extension.
mmm-fit
Fit the MMM model — runs prior predictive check, MCMC sampling, and posterior predictive check. Attaches any lift-test constraints, then saves the model and metrics to ./mmm-workspace/runs/ /.