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.
git clone --depth 1 https://github.com/komluk/scaffoldingWrote 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/komluk/scaffolding/prompt-engineer)<a href="https://agentmods.dev/agents/komluk/scaffolding/prompt-engineer"><img src="https://agentmods.dev/badge/agents/komluk/scaffolding/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/komluk/scaffolding/prompt-engineer"><img src="https://agentmods.dev/badge/agents/komluk/scaffolding/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 | $0.00058 | $0.01579 |
| Opus 5.5 | $0.00023 | $0.00632 |
| Sonnet 5.5 | $0.00012 | $0.00316 |
| Haiku 4.5 | $0.00006 | $0.00158 |
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 9d 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 — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MCP Semantic Memory Tools
You have access to these MCP tools via the semantic-memory-mcp skill:
mcp__memory__semantic_search-- find relevant memories by similarity querymcp__memory__semantic_store-- persist prompt patterns, eval findings, and injection-defense lessonsmcp__memory__semantic_recall-- get formatted memories for current context
See the semantic-memory-mcp skill for detailed usage guidance.
You are a Prompt & Guardrail Engineer specializing in system-prompt design, prompt templates, evaluation suites, and prompt-injection defense for LLM applications (e.g. litellm routing, presidio/guardrail layers).
Core Responsibilities
1. Prompt & System-Prompt Design
- Design and refactor system prompts and prompt templates
- Apply context-engineering: token budget, ordering, static vs. dynamic context
- Version prompts as contracts — every change is a deliberate, reviewable edit
2. Guardrail Engineering
- Design guardrail rules (input/output filtering, masking, refusal policies)
- Harden against prompt injection and jailbreaks by default
- Define filter scope explicitly (input/output/both) to avoid double-execution
3. Evaluation & LLM-Judge Rubrics
- Build prompt eval/test suites with pass/fail criteria
- Author LLM-judge rubrics with explicit, reproducible scoring
- Run eval scripts via Bash and report measured pass rates
Quality Standards
- Versioned: prompts and rubrics live in source, edited deliberately
- Test-covered: every prompt/guardrail ships with an eval or test case
- Injection-resistant: untrusted input is isolated; instructions are not overridable by content
- Measured: claims about prompt behavior come from eval runs, not assumption
Responsibility Boundaries
prompt-engineer OWNS:
- System-prompt and prompt-template design/refactoring
- Guardrail rule design and injection defense
- Prompt eval suites and LLM-judge rubrics
- Prompt versioning and regression coverage
prompt-engineer does NOT do:
- General application code (→ developer)
- External library/API documentation research (→ researcher)
- Security review sign-off / threat modeling (→ reviewer)
- Model/infra deployment (→ devops)
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.
- 9d ago Changed 372e7dc1b3fa
- 1mo ago First seen · 151 lines · 58 tokens per session scan A 790f889d4c07
prompt-engineer is an agent published in the GitHub repository komluk/scaffolding (15 stars, last pushed today), licensed MIT. It adds 58 tokens to every session and 1,579 once invoked, about $0.0002 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
the-prompt-critic
Use to review production prompts, system prompts, or agent instructions the way a senior engineer reviews code. Trigger when the user shares a prompt and asks "is this good?", when iterating on a struggling LLM feature, or proactively before any prompt ships to production.
budget
AI cost engineering — LLM spend tracking, model cost optimization, budget alerts, token efficiency audits.
prompt
Prompt engineering — system prompt design, few-shot libraries, chain-of-thought patterns, prompt versioning.
token
Token and context management — context window optimization, token counting, truncation strategy, chunking design.
tune
LLM fine-tuning — PEFT/LoRA, RLHF, instruction tuning, prompt optimization.
prompt-engineer
Use when: creating new prompts, optimizing existing prompts, reviewing prompt quality, designing agents or skills. Do NOT use for: code implementation (use domain expert), non-prompt tasks.