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 shennawardana23/skillme --skill prompt-optimizergit clone --depth 1 https://github.com/shennawardana23/skillmeWrote 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/shennawardana23/skillme/prompt-optimizer)<a href="https://agentmods.dev/skills/shennawardana23/skillme/prompt-optimizer"><img src="https://agentmods.dev/badge/skills/shennawardana23/skillme/prompt-optimizer/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/shennawardana23/skillme/prompt-optimizer"><img src="https://agentmods.dev/badge/skills/shennawardana23/skillme/prompt-optimizer.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 | $0.00094 | $0.01558 |
| Opus 5 | $0.00047 | $0.00779 |
| Sonnet 5 | $0.00019 | $0.00312 |
| Haiku 4.5 | $0.00009 | $0.00156 |
Grade A, and why
prompt-optimizer 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 8d 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 — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Prompt Optimizer
Turn a vague or underspecified prompt into one that's specific enough to get a good result on the first try — without doing the task itself.
When to Use
- "Optimize this prompt", "improve my prompt", "rewrite this prompt"
- "How should I ask for X", "what's the best way to prompt for..."
- A draft prompt is pasted with a request for feedback or enhancement
Do not use when: the user wants the task done directly ("just do it") — tell them this skill only produces an optimized prompt, and to make a normal task request instead if they want execution.
Role: Advisory Only
Never write code, create files, run commands, or take any implementation action from within this skill. The only output is a diagnosis plus an optimized prompt the user can paste elsewhere to actually run the task.
The Pipeline
Run these phases in order.
Phase 0: Project Detection
Check whether a rules file (CLAUDE.md or equivalent) exists in the working directory and read it for conventions. Detect the tech stack from manifest files present: go.mod → Go, package.json → Node/TypeScript, pyproject.toml/requirements.txt → Python, Cargo.toml → Rust, and so on. If no manifest is found (the prompt is abstract or for a brand-new project), skip detection and flag "tech stack unknown" in Phase 4 rather than guessing one.
Phase 1: Intent Detection
Classify the task into one or more categories: new feature, bug fix, refactor, research, testing, review, documentation, infrastructure, or design. The category shapes which phase-5 workflow steps matter most.
Phase 2: Scope Assessment
Estimate size from the prompt and, if a project was detected, from the affected codebase: trivial (single file, <50 lines), low (single module), medium (multiple components, same domain), high (cross-domain, 5+ files), epic (multi-session, architectural). If no project context exists, estimate from the description alone and mark the estimate as uncertain.
Phase 3: Existing-Skill Matching
What ships with it
1 file 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.
- 8d ago First seen · 107 lines · 94 tokens per session scan A b2c5e7de8b8c
prompt-optimizer is a skill published in the GitHub repository shennawardana23/skillme (2 stars, last pushed 13d ago), licensed Apache-2.0. It adds 94 tokens to every session and 1,558 once invoked, about $0.0005 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 2026-09-03.
Other skills, from other repositories
changelog
Generates a personal markdown changelog of merged or closed pull requests authored by the current user and Linear tickets the user closed or worked on, over a configurable window (default 7 days), grouped by feature area (e.g. Dashboards, Agent0). Inputs sourced from gh search prs --author=@me and the Linear MCP. Use…
dx
Developer Experience (DX) review and advisory skill for CLI tools, shell scripts, developer tooling, and automation. Analyzes code against established CLI design guidelines (clig.dev, Heroku CLI Style Guide, 12 Factor CLI), composability principles, error handling best practices, and developer ergonomics. Triggers on…
disk-cleaner
A Mac disk-cleaning assistant built around the Mole cleanup tool. It checks the environment, previews removable files, and can run cleanup using different safety levels with reports and protected paths.
life-design
Walk you through the Stanford Designing Your Life method and write your Personal Life Design Blueprint — three Odyssey plans and the prototypes to test them.
timeboxed-work
Work under an explicit time budget with deterministic deadline tracking, useful stretch work, scope control, isolated timers for parallel sessions/agents/apps, and handoff. Use when the user asks for a timebox, fixed duration, deadline, work for N minutes/hours, use the full time, keep improving until the deadline…
lark-meeting
A tool for finding and working with online meeting records and related documents in Lark, a workplace collaboration platform. It handles summaries, transcripts, recordings, searchable meeting notes, and live meeting interaction.