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 IchenDEV/prompt-optimizer-plugins --skill optimize-claude-sonnet-5-5-promptsgit clone --depth 1 https://github.com/IchenDEV/prompt-optimizer-pluginsWrote 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/ichendev/prompt-optimizer-plugins/optimize-claude-sonnet-5-5-prompts)<a href="https://agentmods.dev/skills/ichendev/prompt-optimizer-plugins/optimize-claude-sonnet-5-5-prompts"><img src="https://agentmods.dev/badge/skills/ichendev/prompt-optimizer-plugins/optimize-claude-sonnet-5-5-prompts/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/ichendev/prompt-optimizer-plugins/optimize-claude-sonnet-5-5-prompts"><img src="https://agentmods.dev/badge/skills/ichendev/prompt-optimizer-plugins/optimize-claude-sonnet-5-5-prompts.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 | $0.00118 | $0.03159 |
| Opus 5.5 | $0.00047 | $0.01264 |
| Sonnet 5.5 | $0.00024 | $0.00632 |
| Haiku 4.5 | $0.00012 | $0.00316 |
Grade A, and why
optimize-claude-sonnet-5-5-prompts 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 19d 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.
How it starts
The opening of the file, as written. The whole thing — 184 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Optimize Claude Sonnet 5.5 Prompts
Turn rough ideas and existing prompt stacks into copy-ready prompts for Claude Sonnet 5.5. Preserve the user's intent and hard constraints, clarify genuinely blocking gaps, and keep the result no more elaborate than the task requires.
Existing Claude Sonnet 5 prompts should perform well without changes. Most real optimization here is targeted steering for observed behavior plus removal of obsolete workarounds, not a rewrite into a larger template. For the hardest long-horizon work, prefer an Opus model or the select-claude-models skill rather than over-prompting Sonnet.
Use the official basis
Read references/official-guidance.md for model-specific rationale, runtime settings, and migration details. Read references/snippets.md for the copy-ready instruction blocks from Anthropic's guide. Treat the listed URLs as canonical and the prose as a dated working summary; fetch the live pages before making claims about current model IDs, parameters, availability, limits, or pricing.
Use the official model name Claude Sonnet 5.5 and the API model ID claude-sonnet-5-5. Treat Sonnet 5.5, sonnet-5-5, and S5.5 as spelling variants unless context indicates a different product.
When the user is choosing between Sonnet and Opus, or designing a multi-agent Opus-plans / Sonnet-executes setup, use or point to select-claude-models.
Follow the workflow
1. Capture the prompt contract
Identify the following from the user's message, pasted prompt, or referenced file:
- the user-visible outcome and why it matters;
- the inputs, source material, and context Claude will receive;
- hard constraints, facts, policies, and values to preserve;
- the required output, audience, language, and level of detail;
- tools, evidence, or verification the task genuinely depends on;
- whether Claude should assess, recommend, draft, implement, or take external action;
- authorized actions and actions that require approval;
- stopping and fallback behavior when a dependency is unavailable;
- which Sonnet 5.5 behavior the user has actually observed as a problem, and whether the prompt was carried over from Sonnet 5 or an earlier model;
- whether the workload is everyday coding, polished documents, repeated agent tasks, latency-sensitive chat, or something that may belong on Opus instead.
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.
- 19d ago First seen · 184 lines · 118 tokens per session scan A 481450dfd510
optimize-claude-sonnet-5-5-prompts is a skill published in the GitHub repository IchenDEV/prompt-optimizer-plugins (6 stars, last pushed 20d ago), licensed MIT. It adds 118 tokens to every session and 3,159 once invoked, about $0.0005 per session on Opus 5.5. 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 2026-09-30.
Other skills, from other repositories
sol-terra-luna-auto-router
Optimize quality per token across GPT Codex, GPT Work, and Codex CLI by automatically selecting the best-fit GPT-5.6 Luna, Terra, or Sol profile and reasoning effort for the main task and every delegated subtask. Prioritize direct visible Codex execution and importance-aware subagent routing. Use automatically for…
watch
File sentinel that monitors the working directory for changes and marker comments, then auto-triggers appropriate skills. Poll-based via git diff against the last scan commit. Writes intake items for batch processing and routes marker actions through /do. Use for automatic reactions to file changes; do NOT use for…
pr-watch
Local PR watcher. Monitors CI status, automatically fixes failing checks by reading failure logs and applying targeted fixes, then optionally merges when all checks pass. Local CLI analog to Claude Code's cloud auto-fix feature.
live-preview
Mid-build visual verification loop. Takes screenshots of components during construction, not just after. Catches visual regressions and invisible features before they compound. Requires Playwright or similar screenshot tool.
review
5-pass structured code review — correctness, security, performance, readability, consistency.
marshal
Meta-orchestrator that takes any direction — broad, specific, or vague — and autonomously chains skills and context into actionable work. Gathers context from codebase, docs, and memory. Only asks the user when it genuinely cannot proceed. Single-session orchestrator.