Claude Code Prompt Improver is a Claude Code hook that adds useful context and questions around a submitted prompt, tool call, or subagent start. It is for Claude Code users who want clearer requests, better task planning, and fewer correction rounds.
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 agentmods add instructions/severity1/claude-code-prompt-improver/claude-mdgit clone --depth 1 https://github.com/severity1/claude-code-prompt-improverWrote 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/instructions/severity1/claude-code-prompt-improver/claude-md)<a href="https://agentmods.dev/instructions/severity1/claude-code-prompt-improver/claude-md"><img src="https://agentmods.dev/badge/instructions/severity1/claude-code-prompt-improver/claude-md.svg" alt="Measured on agentmods" 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 | $0.05453 | $0.05453 |
| Opus 5 | $0.02727 | $0.02727 |
| Sonnet 5 | $0.01091 | $0.01091 |
| Haiku 4.5 | $0.00545 | $0.00545 |
Grade A, and why
claude-code-prompt-improver CLAUDE.md 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 5d 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 — 250 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Claude Code Prompt Improver
This file provides guidance to Claude Code when working with code in this repository.
Overview
A declarative hook engine driven by a JSON nudge registry. One engine dispatches every hook event; each prompt-improvement capability is a data row in nudges/<EventName>/*.json, not a separate script. Adding an inject-context nudge is a single JSON file with zero Python changes.
Core functionality:
- One engine entry point (
engine.py <EventName>) dispatched per hook event fromhooks.json - Reads stdin once, runs the event's rules, merges
inject_contextfragments by priority, emits one JSON object, exits 0 always improvenudge (always fires on UserPromptSubmit): evaluates clarity; clear prompts proceed, vague prompts invoke the prompt-improver skillapproach-assessmentnudge (UserPromptSubmit, priority 10, keyword match on non-trivial-work verbs, non_slash, ignorecase): injects approach-selection guidance (subagent vs orchestration vs just do it) and reminds that spawned subagents need context passed explicitly; self-cancels false positives with a leading conditionworkflownudge (UserPromptSubmit, priority 20): injects model-routing and plan-mode-first HITL guidance for workflow/deep-research/ultracode requestsplan-modenudge (UserPromptSubmit, priority 50, non_slash, always-evaluate): judges whether task complexity warrants entering plan mode before starting; owns the 'whether to plan at all' decision; approach-assessment owns 'which approach'plannudge (PreToolUse, self-gates on tool_name=EnterPlanMode): injects plan readability guidancesubagent-routingnudge (SubagentStart): injects breadth-over-depth guidance when an Explore or Plan agent spawnsbackground-execnudge (PreToolUse, matches tool_input.command on Bash): encourages background execution and token-efficient polling for long-running/never-exiting commandsoutput-readabilitynudge (UserPromptSubmit, keyword match): self-cancelling reminder to make substantial deliverables (report/review/summary/analysis) human-parsableask-user-questionnudge (UserPromptSubmit, priority 40, keyword match on decision/fork language, non_slash, ignorecase): self-cancelling nudge to route genuine user-owned decisions through AskUserQuestion tool with concrete options; research first when context is thin; pick sensible default for minor/reversible choices- Uses AskUserQuestion tool for targeted clarifying questions (1-6 questions)
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.
- 5d ago First seen · 250 lines · 5,453 tokens per session scan A 11b17b64ec89
claude-code-prompt-improver CLAUDE.md is an instructions file published in the GitHub repository severity1/claude-code-prompt-improver (1,919 stars, last pushed 3mo ago), licensed MIT. It adds 5,453 tokens to every session, about $0.0273 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 instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).