agentmods.dev

system-prompt-engineer

system-prompt-engineer is a skill for Claude Code, Codex from lvcoi/solidJSkills. It costs 36 tokens per session (163 once invoked), scanned A, original, MIT.

A guide for writing and reviewing system prompts, the instructions that control an AI agent’s behavior. It covers instruction priority, safety rules, tool use, fallback behavior, and required output formats.

In plain words
What is it for?
Use it to create or audit operational prompts, define agent constraints, specify evidence requirements, and test realistic scenarios.
Why use it?
It helps reduce ambiguous instructions and inconsistent agent responses. It also checks how the prompt behaves when instructions conflict or information is missing.

Skill for Claude CodeCodex

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

not rated 9repo 8mo ago A scan 36 tokens original MIT

Good fit Use it to create or audit operational prompts, define agent constraints, specify evidence requirements, and test realistic scenarios.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/lvcoi/solidjskills/system-prompt-engineer
View source ↗ lvcoi/solidJSkills
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 lvcoi/solidJSkills --skill system-prompt-engineer
Clone the repo
git clone --depth 1 https://github.com/lvcoi/solidJSkills

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 system-prompt-engineer

README.md
[![agentmods](https://agentmods.dev/badge/skills/lvcoi/solidjskills/system-prompt-engineer/github.svg)](https://agentmods.dev/skills/lvcoi/solidjskills/system-prompt-engineer)
Your own site
<a href="https://agentmods.dev/skills/lvcoi/solidjskills/system-prompt-engineer"><img src="https://agentmods.dev/badge/skills/lvcoi/solidjskills/system-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 system-prompt-engineer

Your own site · 80×15
<a href="https://agentmods.dev/skills/lvcoi/solidjskills/system-prompt-engineer"><img src="https://agentmods.dev/badge/skills/lvcoi/solidjskills/system-prompt-engineer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 36 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 163 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 $0.00036 $0.00163
Opus 5.5 $0.00014 $0.00065
Sonnet 5.5 $0.00007 $0.00033
Haiku 4.5 $0.00004 $0.00016

Measured 2mo ago against content hash 23803e1f881f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

system-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 2mo 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/system-prompt-engineer/SKILL.md · 27 lines

What it actually says

System Prompt Engineer

Build high-clarity prompts that reduce ambiguity and enforce policy.

Authoring Flow

  1. Declare role and domain context.
  2. List non-negotiable constraints and precedence.
  3. Specify tool usage and prohibited actions.
  4. Define required output format and evidence rules.
  5. Add fallback behavior for unknowns and blocked operations.

Validation

  • Test prompt against at least three realistic scenarios.
  • Verify precedence handling under conflicting instructions.
  • Confirm output is structurally consistent.

References

Load references/prompt-audit.md to perform prompt quality review.

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 2mo ago First seen · 27 lines · 36 tokens per session scan A 23803e1f881f

Subscribe to this mod's changes

system-prompt-engineer is a skill published in the GitHub repository lvcoi/solidJSkills (9 stars, last pushed 8mo ago), licensed MIT. It adds 36 tokens to every session and 163 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 2026-08-31.

Building agentsData and AIPrompting
Related

system-prompt-engineer compared with skills from other repositories

system-prompt-engineer next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
system-prompt-engineerlvcoi/solidJSkillsSkill98mo agoMITA36Claude Code, Codex
llm-app-patternsdavila7/claude-code-templatesSkill33kyesterdayMITA54Claude Code, Codex
prompt-engineerJeffallan/claude-skillsSkill12k7d agoMITA93Claude Code
prompt-optimizationlangwatch/langwatchSkill5.0kyesterdayApache-2.0A105Claude Code, Codex
omh-model-optimizationrlaope/oh-my-hermesSkill5.2ktodayMITA84Claude Code, Codex
ideogram4digitalsamba/claude-code-video-toolkitSkill2.5ktodayMITA99Claude Code
prompt-library-for-startupsaws/agent-toolkit-for-awsSkill3.4kyesterdayApache-2.0A228Claude Code