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 iliaal/whetstone --skill refine-promptgit clone --depth 1 https://github.com/iliaal/whetstoneWrote 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/iliaal/whetstone/refine-prompt)<a href="https://agentmods.dev/skills/iliaal/whetstone/refine-prompt"><img src="https://agentmods.dev/badge/skills/iliaal/whetstone/refine-prompt/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/iliaal/whetstone/refine-prompt"><img src="https://agentmods.dev/badge/skills/iliaal/whetstone/refine-prompt.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00062 | $0.00600 |
| Opus 5 | $0.00031 | $0.00300 |
| Sonnet 5 | $0.00012 | $0.00120 |
| Haiku 4.5 | $0.00006 | $0.00060 |
Grade A, and why
refine-prompt 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 10d 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 — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Refining Prompts
Process
- Assess — Identify what the prompt is missing:
| Element | Check |
|---|---|
| Task | Is the core action explicit and unambiguous? |
| Constraints | Are length, format, tone, and scope defined? |
| Output format | Does it specify the expected structure? |
| Context | Does the model have enough background to act? |
| Examples | Would a demonstration clarify the expected output? |
| Edge cases | Are failure modes and boundary conditions addressed? |
-
Rewrite — Transform into specification language: precise, imperative, no filler. Treat the prompt as a spec, not conversation.
-
Validate — Check the rewrite against the assessment table. Every gap identified in step 1 must be addressed.
Rules
- Length: 0.75x–1.5x the original. Conciseness is a feature — add only what's missing, cut what's vague.
- Never invent — only use information present in the original prompt or conversation context. If critical info is missing, ask instead of assuming.
- Instruction hierarchy — order sections by priority: task → constraints → examples → input data → output format. Place the most important instruction first.
- Progressive complexity — start with the simplest prompt that could work. Add few-shot examples, chain-of-thought, or role framing only when the task demands it, not by default.
- Specific verbs — replace vague actions ("analyze", "process", "handle") with measurable ones ("list the top 3", "classify as A/B/C", "return JSON with keys X, Y").
- One output format — specify exactly one format (JSON schema, markdown template, numbered list). Ambiguous format expectations cause inconsistent results.
- No meta-commentary — output only the refined prompt as markdown. No preamble ("Here's an improved version..."), no explanation of changes unless explicitly requested.
Anti-Patterns
| Problem | Fix |
|---|---|
| Vague verbs ("look into", "deal with") | Replace with concrete actions ("list", "compare", "extract") |
| Missing output spec | Add explicit format section with example structure |
| Examples contradict instructions | Align examples to match every stated rule |
| Over-engineered from the start | Strip to simplest working version, then add complexity only where output quality requires it |
| Prompt exceeds context with examples | Limit to 2–3 diverse examples; use one simple, one edge case |
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.
- 10d ago First seen · 48 lines · 62 tokens per session scan A 90212f93f9c5
refine-prompt is a skill published in the GitHub repository iliaal/whetstone (33 stars, last pushed 2d ago), licensed MIT. It adds 62 tokens to every session and 600 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
review-prompt
Review LLM prompts against the prompt-engineering skill's principles — leading with where each line came from — and report the findings without modifying files. Use when reviewing prompt quality, auditing a prompt, evaluating a system prompt, or checking whether prompt issues are high-confidence and fixable.
gemini-prompting
Internal guidance for composing Gemini and AGY prompts for coding, review, diagnosis, and research tasks inside the Gemini Claude Code plugin.
openai
Templates designed for or comparing OpenAI models (GPT-4o, future GPT models).
prompt-optimizer
Optimize prompts for Claude's latest models (Claude 5 family — Opus 5, Sonnet 5, Fable 5 — plus the still-active Opus 4.8, Sonnet 4.6, and Haiku 4.5) using Anthropic's official prompt-engineering guidance. Use when users want to improve, refine, debug, or create prompts or system prompts for Claude. Triggers include…
grok-prompting
Internal guidance for composing Grok prompts for coding, review, diagnosis, and research tasks inside the Grok Claude Code plugin.
shipkit-prompt-audit
Audit LLM prompt pipeline architecture — decomposition, parallelization, chain integrity, schema validation, fallback paths. Finds structural issues no linter catches.