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 escapeboy/ai-prompts --skill optimizegit clone --depth 1 https://github.com/escapeboy/ai-promptsWrote 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/escapeboy/ai-prompts/optimize)<a href="https://agentmods.dev/skills/escapeboy/ai-prompts/optimize"><img src="https://agentmods.dev/badge/skills/escapeboy/ai-prompts/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/escapeboy/ai-prompts/optimize"><img src="https://agentmods.dev/badge/skills/escapeboy/ai-prompts/optimize.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Agent Snooping · line 79 Skill reads from agent configuration directories (.claude/, .codex/, .gemini/). These directories may contain API keys, personal settings, and other credentials that the skill has no legitimate need to access.Fix: Remove all code or instructions that access agent configuration directories (.claude/, .codex/, .gemini/). If configuration values are needed, pass them explicitly as parameters or environment variabl
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 | $0.00051 | $0.01766 |
| Opus 5.5 | $0.00020 | $0.00706 |
| Sonnet 5.5 | $0.00010 | $0.00353 |
| Haiku 4.5 | $0.00005 | $0.00177 |
Grade B, and why
optimize scanned grade B with 1 finding 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 27d 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.
- `metrics` — the savings targets from `~/.claude/settings/token-optimization.json` How it starts
The opening of the file, as written. The whole thing — 163 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/optimize — Maximum Token Efficiency Mode
Activates all Claude Code optimization strategies for the given task. Routes to the correct planning strategy, enforces symbol-first exploration, loads Serena memories, and reports token savings.
Use this as the default way to start any non-trivial work session.
When to Use This Skill (and When NOT to)
| Use this skill for | Use a simpler approach for |
|---|---|
| Starting a non-trivial task (a feature, a refactor, a module) where planning + memory loading pays back | A one-line answer or a question you can answer directly — the strategy/memory scaffolding is pure overhead |
| Work spanning multiple files or subtasks, where symbol-first exploration and model routing save real tokens | A single known edit in a file already open — just make it |
| A task worth measuring — you want the savings report at the end | Trivial edits where reporting savings costs more than the edit |
| Any session where Serena memories + constitution should gate the approach before touching code | A repo with no memories/constitution and a one-shot ask — skip straight to the work |
Start simple. Reach for /optimize only when the task is big enough that choosing a strategy, loading memories, and routing models actually reduces total tokens. For a 1-line fix, the classification step is the overhead this skill exists to avoid elsewhere.
Usage
/optimize [task description]
/optimize [action]
Quick Examples
/optimize "Add email verification to the auth system"
/optimize "Fix the N+1 query in OrdersController#index"
/optimize status
/optimize report
How It Works
When you run /optimize "your task", Claude will:
- Analyze complexity — count subtasks, files affected, and dependencies
- Select planning strategy — Unified (1-2 tasks), Intent-Planning (3-7), or Planning-Only (8+)
- Load context — Serena memories + constitution (if available)
- Apply symbol-first exploration — never reads full files before checking symbols
- Select optimal model — Haiku for simple steps, Sonnet for complex work, Opus only for critical decisions
- Execute with metrics — reports token savings at the end
What ships with it
3 files 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.
- 27d ago Changed 401b23b77759
- 1mo ago First seen · 163 lines · 51 tokens per session scan B 91f79fc5969b
optimize is a skill published in the GitHub repository escapeboy/ai-prompts (91 stars, last pushed 15d ago), licensed MIT. It adds 51 tokens to every session and 1,766 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
agentmail
Use your assigned AgentMail inbox to read email tasks, explicitly send or reply, and check delivery. Provided automatically by your inbox assignment.
rowboat-spaces
How to work as a member of Rowboat Spaces, the team chat where people and agents work together. Load it once per session, before acting on any request that reaches you from Rowboat; it covers your setup, mentions and hand-offs, the tools, and files.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
mochi-remind
Handle due reminders — notify the user with natural language and mark them done.