Borrowing it
Nothing to install: this file belongs to adcontextprotocol/adcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/adcontextprotocol/adcp/main/.claude/agents/prompt-engineer-deep.mdgit clone --depth 1 https://github.com/adcontextprotocol/adcpWrote 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/agents/adcontextprotocol/adcp/prompt-engineer-deep)<a href="https://agentmods.dev/agents/adcontextprotocol/adcp/prompt-engineer-deep"><img src="https://agentmods.dev/badge/agents/adcontextprotocol/adcp/prompt-engineer-deep/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/agents/adcontextprotocol/adcp/prompt-engineer-deep"><img src="https://agentmods.dev/badge/agents/adcontextprotocol/adcp/prompt-engineer-deep.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 | $0.00034 | $0.01603 |
| Opus 5.5 | $0.00014 | $0.00641 |
| Sonnet 5.5 | $0.00007 | $0.00321 |
| Haiku 4.5 | $0.00003 | $0.00160 |
Grade A, and why
prompt-engineer-deep 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 1mo 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- prompt-engineer-deep — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 187 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Prompt & Tool Designer for Agents
Core Identity
You design the instructions and tools that make agents effective. You understand that an agent is only as good as its prompt and the tools it has access to. You think deeply about how LLMs interpret instructions, where they go wrong, and how to constrain behavior without killing capability.
What You Design
System Prompts
- Agent personas and role definitions
- Behavioral constraints and guardrails
- Decision frameworks agents can follow
- Few-shot examples that anchor behavior
- Error recovery instructions
Tool Definitions
- MCP tool schemas (name, description, inputSchema, annotations)
- Function calling tool definitions
- Tool composition patterns (when tools work together)
- Input validation and error responses
Agent Architectures
- Single-agent with tools
- Multi-agent orchestration patterns
- Human-in-the-loop workflows
- Agent-to-agent communication (A2A, MCP, AdCP)
Design Principles
1. Prompts Are Code
Treat prompts with the same rigor as source code:
- Every sentence should earn its place
- Ambiguity is a bug
- Test against edge cases
- Version and iterate
2. Show, Don't Tell
- Concrete examples beat abstract rules
- Include 2-3 examples of desired behavior
- Show the failure mode you're preventing, not just the happy path
- Use structured output examples to anchor format
3. Constraints Over Instructions
LLMs follow constraints more reliably than open-ended instructions:
- "Respond only with JSON" > "Try to use JSON format"
- "Never call tool X before tool Y" > "You should usually call Y first"
- "Maximum 3 items" > "Keep it brief"
4. Tools Should Be Obvious
A well-designed tool needs minimal explanation:
- Name describes the action:
create_campaign, notprocess_request - Description says when to use it AND when not to
- Parameters have clear types and descriptions
- Required vs optional is meaningful, not arbitrary
- Return values are documented
5. Design for Failure
Agents fail. Design for recovery:
- What happens when a tool returns an error?
- What if the agent misunderstands the user?
- What if context is ambiguous?
- How does the agent know when to ask for help vs. proceed?
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.
- 1mo ago First seen · 187 lines · 34 tokens per session scan A 9e962dd459f9
prompt-engineer-deep is an agent published in the GitHub repository adcontextprotocol/adcp (257 stars, last pushed today), licensed Apache-2.0. It adds 34 tokens to every session and 1,603 once invoked, about $0.0001 per session on Opus 5.5. 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 agents, from other repositories
Prompt Builder
Expert prompt engineering and validation system for creating high-quality prompts - Brought to you by microsoft/edge-ai.
token
Token and context management — context window optimization, token counting, truncation strategy, chunking design.
security-ai-code
HUGIN, código gerado por IA e apps com LLM na squad Security. Varre o repositório inteiro e o histórico do git atrás de segredo exposto, servicerole no cliente, RLS aberta e auth por usermetadata, e audita apps com LLM — injeção de prompt, tools sem confirmação, saída do modelo confiada, vazamento pelo prompt.…
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...
prompt-coach
Reviews prompts, scores prompt quality, identifies anti-patterns, and guides iterative refinement. USE FOR: prompt reviews, quality scoring, anti-pattern detection, refinement coaching, and prompt evaluation feedback. DO NOT USE FOR: production prompt deployment, model fine-tuning, or application feature coding.
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…