agents-in-production

agents-in-production is a skill for Claude Code, Codex from thaolst/ai-growth-agents-for-marketers. It costs 79 tokens per session (373 once invoked), scanned A, original, MIT.

A checklist for reviewing an AI agent before putting its prompt or workflow into real use. It examines weaknesses, unusual inputs, suggested improvements, monitoring signs, and whether the agent is ready to deploy.

In plain words
What is it for?
Use it to review an agent description, system prompt, example input, and example output before deployment, then decide whether to launch, test further, or redesign.
Why use it?
It helps uncover likely failures before the agent is used in real campaigns or other production work. It focuses on practical failure cases rather than only theoretical concerns.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to review an agent description, system prompt, example input, and example output before deployment, then decide whether to launch, test further, or redesign.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/thaolst/ai-growth-agents-for-marketers/agents-in-production
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.

Any agent
npx skills add thaolst/ai-growth-agents-for-marketers --skill agents-in-production
Clone the repo
git clone --depth 1 https://github.com/thaolst/ai-growth-agents-for-marketers

Made for: Claude Code, Codex.

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 agents-in-production

README.md
[![agentmods](https://agentmods.dev/badge/skills/thaolst/ai-growth-agents-for-marketers/agents-in-production/github.svg)](https://agentmods.dev/skills/thaolst/ai-growth-agents-for-marketers/agents-in-production)
Your own site
<a href="https://agentmods.dev/skills/thaolst/ai-growth-agents-for-marketers/agents-in-production"><img src="https://agentmods.dev/badge/skills/thaolst/ai-growth-agents-for-marketers/agents-in-production/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 agents-in-production

Your own site · 80×15
<a href="https://agentmods.dev/skills/thaolst/ai-growth-agents-for-marketers/agents-in-production"><img src="https://agentmods.dev/badge/skills/thaolst/ai-growth-agents-for-marketers/agents-in-production.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 79 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 373 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 $0.00079 $0.00373
Opus 5 $0.00039 $0.00187
Sonnet 5 $0.00016 $0.00075
Haiku 4.5 $0.00008 $0.00037

Measured 12d ago against content hash d84e76741eee, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

agents-in-production 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 12d 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.

skills/agents-in-production/SKILL.md · 55 lines

What it actually says

Agents in Production — Pre-Deploy Review

Bạn là expert review AI prompt trước khi deploy vào thực tế.

Input cần có

  • Mô tả agent: làm gì, nhận input gì, trả về output gì
  • System prompt đang dùng
  • Ví dụ input thật
  • Output agent trả về với input đó

Output format

Điểm yếu của prompt

Chỗ nào có thể cho kết quả không nhất quán hoặc sai?

Edge cases chưa xử lý

Input bất thường nào có thể làm agent fail?

Cải thiện đề xuất

Thay đổi cụ thể trong prompt để output ổn định hơn.

Monitoring

Dấu hiệu nào cho thấy agent đang degraded khi chạy thật?

Verdict

Deploy ngay, cần test thêm, hay cần thiết kế lại?

Nguyên tắc

Tập trung vào lỗi thực tế, không phải lỗi lý thuyết. Nếu use case an toàn để deploy với một số hạn chế, nói rõ hạn chế đó thay vì chặn hoàn toàn.


English

You are an expert reviewing an AI prompt before production deployment.

Focus on real failure modes, not theoretical ones. If the use case is safe to deploy with some limitations, state those limitations clearly rather than blocking deployment entirely.

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. 12d ago First seen · 55 lines · 79 tokens per session scan A d84e76741eee

Subscribe to this mod's changes

agents-in-production is a skill published in the GitHub repository thaolst/ai-growth-agents-for-marketers (5 stars, last pushed 1mo ago), licensed MIT. It adds 79 tokens to every session and 373 once invoked, about $0.0004 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 skills, from other repositories

mem0-test-integration

Verify a Mem0 integration produced by /mem0-integrate. Runs in the same workspace on the same branch (loose coupling) — installs dependencies, runs the repo's native test suite, then exercises a real end-to-end smoke flow against the user's API key. Produces a scorecard. TRIGGER when: user has just run /mem0-integrate…

mem0ai/mem0 · 207 tokens

promptfoo-provider-setup

Configure promptfoo providers or redteam targets for hosted models, live HTTP APIs, Python/JavaScript local scripts, agent SDKs, or multi-input systems. Use when connecting promptfoo to the system under test, mapping vars, auth env vars, request bodies, response transforms, or static-code-derived provider wrappers. Do…

promptfoo/promptfoo · 91 tokens

darwinian-evolver

Evolve prompts/regex/SQL/code with Imbue's evolution loop.

NousResearch/hermes-agent · 22 tokens

evaluating-with-leakage-gates

Evaluate an OpenMed de-identification or clinical NER model against the leakage-first release gates G1a through G8, which gate releases on residual PHI leakage rather than on F1. Use when the user wants to run the OpenMed eval harness on a synthetic golden set, decide whether a de-id model is RELEASABLE or…

maziyarpanahi/openmed · 158 tokens

bat-story-eval

Compare MCP tool behavior between target and baseline versions using pre-built and custom stories with diff-based triage.

homeassistant-ai/ha-mcp · 26 tokens

connect-agent

Connect the codebase's AI agent to LangWatch agent simulations, so test suites run against the real agent process. Adds a small connect function beside the service startup that calls the agent already in the codebase, which opens an outbound connection and registers the agent with its environment and its run…

langwatch/langwatch · 102 tokens