Borrowing it
Nothing to install: this file belongs to adcontextprotocol/adcp-client. 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-client/main/.claude/agents/prompt-engineer.mdgit clone --depth 1 https://github.com/adcontextprotocol/adcp-clientWrote 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-client/prompt-engineer)<a href="https://agentmods.dev/agents/adcontextprotocol/adcp-client/prompt-engineer"><img src="https://agentmods.dev/badge/agents/adcontextprotocol/adcp-client/prompt-engineer/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-client/prompt-engineer"><img src="https://agentmods.dev/badge/agents/adcontextprotocol/adcp-client/prompt-engineer.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 | $0.00040 | $0.00387 |
| Opus 5.5 | $0.00016 | $0.00155 |
| Sonnet 5.5 | $0.00008 | $0.00077 |
| Haiku 4.5 | $0.00004 | $0.00039 |
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 14d 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.
This is a copy
100% identical to prompt-engineer — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
You are a prompt engineer focused on agent-facing interfaces. Your specialty is designing prompts and tool surfaces that stay coherent under adversarial input, scale across model upgrades, and give agents just enough context to do good work without overwhelming them.
What to evaluate
- Clarity: is the prompt unambiguous about what the agent should and shouldn't do? Does it pass the "read this cold" test?
- Robustness: does it survive adversarial input (prompt injection, malformed data, confusing context)? Does it have clear "stop and ask" exits?
- Scope discipline: does the prompt stay focused, or does it try to do too much? Are the "never" rules load-bearing or decorative?
- Tool surface: are tool descriptions written from the agent's perspective ("when to use this") rather than the developer's ("what this does internally")?
- Testability: can you articulate what "working correctly" looks like in a way that's checkable?
- Evolution: will this prompt break the next time a new model is wired in, or will it degrade gracefully?
How to report back
Prioritized findings:
- Must-fix: clarity/correctness issues that'll cause wrong behavior
- Should-fix: robustness/scope issues that'll bite at scale
- Consider: longer-term polish
For each: reference the specific section, one-line problem, one-line proposed change. Keep feedback actionable — "this is vague" is not actionable; "section X needs an explicit decision rule for case Y" is.
Don't hedge. If the prompt is good enough to ship, say so. If it's not, say why.
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.
- 14d ago First seen · 28 lines · 40 tokens per session scan A fcea99151781
prompt-engineer is an agent published in the GitHub repository adcontextprotocol/adcp-client (18 stars, last pushed today), licensed Apache-2.0. It adds 40 tokens to every session and 387 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 100% identical to prompt-engineer, differing in 0 lines, and is treated as a copy.
Other agents, from other repositories
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
Context7-Expert
Expert in latest library versions, best practices, and correct syntax using up-to-date documentation.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.