timps_prompt_engineer

timps_prompt_engineer is an agent for Claude Code from Sandeeprdy1729/timps-swarm. It costs 54 tokens per session (478 once invoked), scanned A, a copy of timps_ab_testing_agent, MIT.

A specialist for rewriting instructions given to language models. It uses structured prompts, reasoning guidance and examples to shape the model's output.

In plain words
What is it for?
Use it to improve prompts for chatbots, agents and other language-model tasks.
Why use it?
It helps when a prompt produces inconsistent, incomplete or poorly formatted answers.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter; mentions subagents.

Good fit Use it to improve prompts for chatbots, agents and other language-model tasks.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/sandeeprdy1729/timps-swarm/timps-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/Sandeeprdy1729/timps-swarm

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 timps_prompt_engineer

README.md
[![agentmods](https://agentmods.dev/badge/agents/sandeeprdy1729/timps-swarm/timps-prompt_engineer/github.svg)](https://agentmods.dev/agents/sandeeprdy1729/timps-swarm/timps-prompt_engineer)
Your own site
<a href="https://agentmods.dev/agents/sandeeprdy1729/timps-swarm/timps-prompt_engineer"><img src="https://agentmods.dev/badge/agents/sandeeprdy1729/timps-swarm/timps-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.

agentmods 80×15 button for timps_prompt_engineer

Your own site · 80×15
<a href="https://agentmods.dev/agents/sandeeprdy1729/timps-swarm/timps-prompt_engineer"><img src="https://agentmods.dev/badge/agents/sandeeprdy1729/timps-swarm/timps-prompt_engineer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 54 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 478 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 84% copy Near-identical to another mod 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 $0.00054 $0.00478
Opus 5 $0.00027 $0.00239
Sonnet 5 $0.00011 $0.00096
Haiku 4.5 $0.00005 $0.00048

Measured 5d ago against content hash 807db4ce9574, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

timps_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 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.

Origin

This is a copy

84% identical to timps_ab_testing_agent — 16 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.

.claude/agents/timps-prompt_engineer.md · 45 lines

What it actually says

prompt engineer

You are the prompt engineer sub-agent from the TIMPS Swarm (category: priority).

Your job

Rewrite prompts with Chain-of-Thought, XML tags, and few-shot examples for better LLM output.

How to respond

  1. Always call the MCP tool timps_prompt_engineer exactly once via the mcp__timps-swarm__timps_prompt_engineer tool handle.
  2. Pass the user's request verbatim in the input — do not summarise, do not pre-empt.
  3. Wait for the tool's text response and return it to the parent agent. The tool output is the result.
  4. Do not try to answer from your own knowledge — this sub-agent exists to route to the TIMPS specialist.
  5. Do not call any other TIMPS tool unless the user explicitly asks for a different agent.

What you do NOT do

  • Do not run shell commands, read files, or edit code — those are the parent agent's job.
  • Do not chain multiple TIMPS tools — one tool call per sub-agent invocation.
  • Do not modify the request payload (add fields, change casing, etc.) — forward as-is.

Input contract

The MCP tool timps_prompt_engineer accepts a JSON object. Pass through whatever the parent agent provided. Common shapes:

{ "request": "<plain-English task>" }

or for the structured agents:

{ "code": "...", "language": "python", "goals": ["reduce_complexity"] }

Refer to the parent agent's invocation — do not invent parameters.

Output contract

Return the tool's text content verbatim to the parent agent. Do not wrap it in extra markdown headings, do not add commentary. The parent will integrate it into the user's final answer.

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 First seen · 45 lines · 54 tokens per session scan A 807db4ce9574

Subscribe to this mod's changes

timps_prompt_engineer is an agent published in the GitHub repository Sandeeprdy1729/timps-swarm (1 stars, last pushed 6d ago), licensed MIT. It adds 54 tokens to every session and 478 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. It is 84% identical to timps_ab_testing_agent, differing in 16 lines, and is treated as a copy.

Related

Other agents, from other repositories

prompt-engineer

Author and adapt prompts — discover, draft, deliver — under HITL approvals. Full subagent.

griddynamics/rosetta · 24 tokens

token

Optimizes LLM context windows through token budgeting, chunking strategy, and truncation design. Use when you need to control token spend, design a chunking pipeline, or audit token usage in a production AI system. Trigger with "design my token budget", "fix my context overflow".

jeremylongshore/tons-of-skills-marketplace · 60 tokens

tune

Designs LLM fine-tuning pipelines using PEFT/LoRA, RLHF, and instruction datasets, and systematically optimizes prompts before recommending fine-tuning. Use when prompt engineering alone isn't achieving target quality or you need a smaller, cheaper model for a specific task. Trigger with "design a fine-tuning…

jeremylongshore/tons-of-skills-marketplace · 74 tokens

ai-engineer

Build LLM applications, RAG systems, and prompt pipelines. Implements vector search, agent orchestration, and AI API integrations. Use PROACTIVELY for LLM features, chatbots, or AI-powered applications.

echoVic/blade-code · 48 tokens

FAI DSPy Expert

DSPy framework specialist — declarative LM programs, signature-based modules, optimizers (BootstrapFewShot, MIPRO), assertions, metric-driven prompt optimization, and compiled prompt pipelines.

frootai/frootai · 43 tokens

report-generator

Performs blind comparison of repeated prompt-execution pairs, then maps observed differences to optimization findings after identity reveal. Use when original and optimized prompt trials are available.

shinpr/rashomon · 35 tokens