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 skills/mbanderas/maestro/maestro-token-efficiencynpx skills add mbanderas/maestro --skill maestro-token-efficiencygit clone --depth 1 https://github.com/mbanderas/maestroWrote 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/mbanderas/maestro/maestro-token-efficiency)<a href="https://agentmods.dev/skills/mbanderas/maestro/maestro-token-efficiency"><img src="https://agentmods.dev/badge/skills/mbanderas/maestro/maestro-token-efficiency.svg" alt="Measured on agentmods" 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 | $0.00029 | $0.00235 |
| Opus 5 | $0.00015 | $0.00118 |
| Sonnet 5 | $0.00006 | $0.00047 |
| Haiku 4.5 | $0.00003 | $0.00023 |
Grade A, and why
maestro-token-efficiency 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 4d 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
Maestro Token Efficiency
Use this skill for Maestro repo changes that affect agent context, instruction loading, benchmark search hygiene, or Codex behavior.
- Read
docs/agent-map.mdfirst for navigation. - Prefer benchmark summary files over raw streams unless doing
forensic scoring. Use
rg --no-ignorefor raw stream audits. - Preserve Maestro's quality bar: no weaker verification status, no hidden-oracle exposure, and no default behavior change without benchmark evidence.
- For Codex-specific behavior, check
docs/codex.mdand current official Codex docs before changing durable guidance. - Keep always-loaded instruction files stable. Put volatile run notes,
dated scratch state, machine-local paths, and benchmark deltas in
summaries or checkpoints, not
AGENTS.md/adapters.
Before completion after edits, run:
npm test
npm run lint
npm run bench-verify
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.
- 4d ago First seen · 30 lines · 29 tokens per session scan A 3217d152093b
maestro-token-efficiency is a skill published in the GitHub repository mbanderas/maestro (5 stars, last pushed yesterday), licensed MIT. It adds 29 tokens to every session and 235 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 2026-08-31.
Other skills, from other repositories
fetch-url
Fetch a single URL and convert its content to Markdown. Use when you need to read a web page, documentation page, or API reference without indexing it. The content is returned as plain Markdown text on stdout.
firebase-messaging
Use when setting up Firebase Cloud Messaging, managing permissions and tokens, handling background/foreground notification taps, or dispatching messages server-side (HTTP v1).
karpathy-llm-wiki
Use when building or maintaining a personal LLM-powered knowledge base. Triggers: ingesting sources into a wiki, querying wiki knowledge, linting wiki quality, 'add to wiki', 'what do I know about', or any mention of 'LLM wiki' or 'Karpathy wiki'.
firebase-cloud-functions
Use when calling callable functions (httpsCallable), passing data to server-side logic, handling function errors/timeouts, configuring regions, or testing with the Emulator Suite.
accessibility
Use when working on accessibility, a11y, WCAG, ARIA, screen readers, keyboard nav, focus order, contrast, alt text, captions, reduced motion, or target sizes; not language/culture/device (see inclusive-design).
excalidraw-architect
Choose and compose the right Excalidraw diagram - architecture, flowchart, sequence, state, ER, swimlane, process, timeline, quadrant, pyramid, venn, loop, gantt, bar, line, scatter, and more - using the excalidraw-architect-mcp server. Use whenever a reader would learn more from a picture than from prose, or when…