Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/mhmdreza-rafiei/agent-toolsnpx agentmods add skills/mhmdreza-rafiei/agent-tools/enhance-promptWrote 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/mhmdreza-rafiei/agent-tools/enhance-prompt)<a href="https://agentmods.dev/skills/mhmdreza-rafiei/agent-tools/enhance-prompt"><img src="https://agentmods.dev/badge/skills/mhmdreza-rafiei/agent-tools/enhance-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/mhmdreza-rafiei/agent-tools/enhance-prompt"><img src="https://agentmods.dev/badge/skills/mhmdreza-rafiei/agent-tools/enhance-prompt.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 | $0.00121 | $0.04256 |
| Opus 5 | $0.00060 | $0.02128 |
| Sonnet 5 | $0.00024 | $0.00851 |
| Haiku 4.5 | $0.00012 | $0.00426 |
Grade A, and why
enhance-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 9d 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 — 345 lines — stays where its author put it; the contents beside it link to each section on GitHub.
enhance-prompt
Rewrite the user’s message into a precise, portable agent prompt. Enhance = clarify and structure — never strip user-stated details that affect accuracy. Accuracy first; tokens second (same or better meaning, fewer tokens).
Do not invent requirements or paste workspace-local paths/stack. For shape and examples, open references/TEMPLATE.md and references/SECTIONS.md.
Usage modes
The user picks how the enhanced prompt is delivered. Parse from invocation:
| Invocation | Mode | Behavior |
|---|---|---|
/enhance-prompt or enhance-prompt (no suffix) |
auto |
Default. Run passes 0-11; then decide (see auto rules below). |
enhance-prompt auto / enhance-prompt auto use |
auto |
Same as default. |
enhance-prompt manual / enhance-prompt manual use |
manual |
Emit the enhanced prompt in chat only. Do not execute the task. |
enhance-prompt self / enhance-prompt self use |
self |
Enhance internally, then execute the task. Do not paste the full enhanced prompt in chat unless the user also asked to show it (e.g. "and show me the prompt"). |
Aliases: enhance and use / enhance then do it -> self. just enhance / enhance only -> manual.
Auto mode (default)
After enhancing, choose execute vs emit:
Execute internally (same chat behavior as self) when all are true:
- The task is actionable in the current workspace (files, repo, or tools the agent can touch now).
- The user did not ask for a portable prompt for another project, agent, or session.
- The user did not say "only enhance", "don't run", "manual", or equivalent.
- No blocking open questions remain (pass 0).
Emit prompt only (same as manual) when any is true:
- User wants a prompt to paste elsewhere ("for Claude", "for another repo", "copy-ready").
- Task targets a workspace the agent cannot act in.
- User said enhance-only / manual / do not execute.
- Blocking ambiguities need answers before work can start.
What ships with it
2 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.
- 9d ago First seen · 345 lines · 121 tokens per session scan A a50280c5065f
enhance-prompt is a skill published in the GitHub repository mhmdreza-rafiei/agent-tools (5 stars, last pushed 25d ago), licensed MIT. It adds 121 tokens to every session and 4,256 once invoked, about $0.0006 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…