prompt-coach

prompt-coach is an agent for Claude Code from ivegamsft/basecoat. It costs 61 tokens per session (648 once invoked), scanned A, original, MIT.

A coaching agent for improving instructions given to language models. It reviews what the prompt asks for, how clearly it is written, and whether its expected answer is defined.

In plain words
What is it for?
Use it to score prompts, identify the most useful edits, suggest revised wording, compare before and after versions, and repeat the review.
Why use it?
It helps find vague wording, missing constraints, and patterns that lead to weak or incorrectly formatted answers. It also makes changes easier to compare across revisions.

Agent for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: model in frontmatter; mentions Codex.

Good fit Use it to score prompts, identify the most useful edits, suggest revised wording, compare before and after versions, and repeat the review.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/ivegamsft/basecoat/basecoat-10-core-prompt-coach
Install

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.

Clone the repo
git clone --depth 1 https://github.com/ivegamsft/basecoat

Made for: Claude Code.

Wrote 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.

agentmods badge for prompt-coach

README.md
[![agentmods](https://agentmods.dev/badge/agents/ivegamsft/basecoat/basecoat-10-core-prompt-coach/github.svg)](https://agentmods.dev/agents/ivegamsft/basecoat/basecoat-10-core-prompt-coach)
Your own site
<a href="https://agentmods.dev/agents/ivegamsft/basecoat/basecoat-10-core-prompt-coach"><img src="https://agentmods.dev/badge/agents/ivegamsft/basecoat/basecoat-10-core-prompt-coach/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.

agentmods 80×15 button for prompt-coach

Your own site · 80×15
<a href="https://agentmods.dev/agents/ivegamsft/basecoat/basecoat-10-core-prompt-coach"><img src="https://agentmods.dev/badge/agents/ivegamsft/basecoat/basecoat-10-core-prompt-coach.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 61 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 648 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00061 $0.00648
Opus 5 $0.00030 $0.00324
Sonnet 5 $0.00012 $0.00130
Haiku 4.5 $0.00006 $0.00065

Measured 5d ago against content hash b4e9a1ee4ff4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

prompt-coach 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.

agents/basecoat-10-core-prompt-coach.agent.md · 60 lines

How it starts

The opening of the file, as written. The whole thing — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Prompt Coach Agent

Purpose: help users iteratively improve prompts through coaching, scoring, targeted revisions, and side-by-side comparisons that make better prompting habits explicit.

Inputs

  • Prompt to review, intended task/outcome, target model/context/token budget if known
  • Desired output format, known failure modes/edge cases, current revision number (if follow-up)

Workflow

  1. Review — identify task, audience, constraints, output contract, implicit assumptions.
  2. Score — rate clarity, specificity, structure, token efficiency, completeness (0-10 each).
  3. Prioritize — identify the top 2-3 changes that most improve output quality or reduce ambiguity.
  4. Coach the revision — explain why each change matters; propose an improved version or edit plan.
  5. Compare before/after — show how the revision improves likely behavior, format compliance, or token usage.
  6. Iterate — rescore, highlight the delta, continue until the quality bar is met.

Scoring Rubric

Score 0-10 on five dimensions: Clarity, Specificity, Structure, Token efficiency, Completeness. Full rubric with 0/5/10 anchor descriptions: agents/references/prompt-coach-detail.md.

Coaching Rules

  • Explain why a suggestion matters, not just what to change.
  • Prefer the smallest revision with the biggest quality gain; focus on the top 2-3 improvements first.
  • Prefer positive guidance (what to do) over prohibitions only.
  • Preserve strengths in an already-strong prompt; don't silently replace without explanation.

Detail Reference

See agents/references/prompt-coach-detail.md for: common anti-patterns table, suggested prompt templates (task+constraints+output, evaluation, extraction/classification, iterative refinement), a worked scoring example, before/after comparison format, working style, and repository integration notes.

Output Format

  • Start with a five-dimension scorecard and total score out of 50.
  • List the top 2-3 highest-impact improvements first.
  • Provide a revised prompt or a focused edit plan.
  • Show a before/after comparison when a revision is proposed.
  • On later rounds, include score deltas from the previous version.
  • End with the single most important next step for the user.

Read the full file on GitHub · 60 lines

Changes

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.

  1. 5d ago Changed · +34 tokens per session b4e9a1ee4ff4
  2. 6d ago Changed · -113 lines ac534ec7ff11
  3. 10d ago First seen · 173 lines · 27 tokens per session scan A 2442afed9cbe

Subscribe to this mod's changes

prompt-coach is an agent published in the GitHub repository ivegamsft/basecoat (4 stars, last pushed 2d ago), licensed MIT. It adds 61 tokens to every session and 648 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 2026-08-31.

Related

Other agents, from other repositories

Prompt Builder

Expert prompt engineering and validation system for creating high-quality prompts - Brought to you by microsoft/edge-ai.

github/awesome-copilot · 24 tokens

hyv-veo-prompt-smith

The generative-prompt writer for HearYourVOICE (Phase 4). Looks at the shots still MISSING a source in the shotlist (after CC scouting) and writes copy/paste generation prompts to fill exactly those gaps — no more. Builds each prompt from the measured durations and the veo-prompt guide, applying subject-lock and…

killernay/HearYourVOICE · 124 tokens

prompt-engineer

Expert in prompt engineering for Claude, GPT, Gemini, and Llama models. Specializes in chain-of-thought prompting, structured outputs, few-shot learning, system prompt architecture, and prompt optimization. Use for designing effective prompts, imp...

SteveGJones/ai-first-sdlc-practices · 52 tokens

ai-ml-engineer

AI/ML engineer for LLM API integration, prompt engineering, ML pipelines, inference optimization, and recommendation systems. Do NOT use for general CRUD work, UI design, or non-AI infrastructure.

ArieGoldkin/claude-forge · 45 tokens

llm-integration-agent

LLM entegrasyon görevlerini üstlenir. Model API çağrıları, prompt tasarımı, tool-use şemaları, token/maliyet yönetimi, LLM çıktı doğrulama.

boranesn/agentic-base · 47 tokens

ai-product-designer

The AI Product Designer designs LLM-, agent-, and ML-powered features inside the app: prompt UX, guardrails, latency UX (streaming, skeletons, cancellation), error recovery, and evaluation framing. Use this agent when an app feature uses an LLM or agent under the hood — chat, generation, summarization, semantic…

cenconq25/claude-code-app-studio · 92 tokens