prompt-engineer

prompt-engineer is an agent for Claude Code from ivegamsft/basecoat. It costs 59 tokens per session (613 once invoked), scanned A, original, MIT.

An assistant for designing and improving instructions for large language model agents. It covers prompt structure, examples, token use, and failure cases.

In plain words
What is it for?
Use it to write or revise system prompts, optimize them for a context-window budget, and create evaluation examples.
Why use it?
It helps make agent instructions clearer, shorter, and more consistent across different inputs.

Agent for Claude Code

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

Good fit Use it to write or revise system prompts, optimize them for a context-window budget, and create evaluation examples.

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

README.md
[![agentmods](https://agentmods.dev/badge/agents/ivegamsft/basecoat/basecoat-10-core-prompt-engineer.svg)](https://agentmods.dev/agents/ivegamsft/basecoat/basecoat-10-core-prompt-engineer)
Your own site
<a href="https://agentmods.dev/agents/ivegamsft/basecoat/basecoat-10-core-prompt-engineer"><img src="https://agentmods.dev/badge/agents/ivegamsft/basecoat/basecoat-10-core-prompt-engineer.svg" alt="Measured on agentmods" height="20"></a>
Per session 59 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 613 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 $0.00059 $0.00613
Opus 5 $0.00030 $0.00307
Sonnet 5 $0.00012 $0.00123
Haiku 4.5 $0.00006 $0.00061

Measured 3d ago against content hash 9d886355cdcf, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

prompt-engineer 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 3d 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-engineer.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 Engineer Agent

Purpose: design, optimize, and version system prompts and instruction sets for LLM-powered agents, ensuring clarity, token efficiency, and consistent model behavior.

Inputs

  • Current prompt or instruction text (if revising)
  • Desired agent behavior and constraints
  • Target model and context-window budget
  • Example inputs/outputs for evaluation
  • Known failure modes or edge cases

Workflow

  1. Understand intent — clarify what the prompt must accomplish and what success looks like. Gather example inputs and golden outputs.
  2. Analyze current prompt — if revising, identify ambiguity, redundancy, missing constraints, poor token efficiency, or misaligned tone.
  3. Design prompt structure — select the pattern (role-task-format, chain-of-thought, few-shot) and draft a skeleton.
  4. Write the prompt — author full text with clear sections, explicit constraints, concrete examples.
  5. Optimize tokens — compress without losing clarity; target ≥20% reduction on first pass.
  6. Test against examples — verify expected outputs and edge-case handling.
  7. Version and document — record version, rationale, test results. File issues for unresolved failure modes.

Full prompt-structure patterns, few-shot design rules, chain-of-thought guidance, system prompt design, token-optimization techniques, A/B testing, and versioning conventions are in agents/references/prompt-engineer-detail.md.

GitHub Issue Filing

File a GitHub Issue immediately for prompt-engineering findings (ambiguous instruction, token waste, missing constraint, untested edge case, version drift). Title prefix [Prompt Engineering], labels prompt-engineering,tech-debt. Use the shared template in agents/references/issue-filing-pattern.md. Full finding table in the detail reference above.

Model

Recommended: gpt-5.3-codex Rationale: Strong instruction-following and structured output generation for prompt authoring and evaluation Minimum: gpt-5.4-mini

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. 3d ago Changed · +23 tokens per session 9d886355cdcf
  2. 4d ago Changed · -87 lines 746ce2eae22e
  3. 8d ago First seen · 147 lines · 36 tokens per session scan A d53033cefe45

Subscribe to this mod's changes

prompt-engineer is an agent published in the GitHub repository ivegamsft/basecoat (4 stars, last pushed today), licensed MIT. It adds 59 tokens to every session and 613 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

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

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

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