author-agent-instructions

author-agent-instructions is a skill for Claude Code, Codex from baldaworks/promptkitty. It costs 75 tokens per session (878 once invoked), scanned A, a copy of promptkitty-author-agent-instructions, MIT.

Instructions for turning a completed PromptKit prompt into permanent project guidance or a provider-specific subagent profile. A subagent is a specialized AI helper configured for a particular coding tool.

In plain words
What is it for?
Use it to create project instruction files or subagent profiles for Codex, Claude Code, Grok Build, GitHub Copilot, OpenCode, Cursor, and other listed providers.
Why use it?
It provides a defined process for converting reusable behavior into files that coding agents can load. It also requires the source prompt and provider rules to be resolved before writing those files.

Skill for Claude CodeCodex

Written for Claude Code and Codex: shipped in a Claude Code plugin, but also agents/openai.yaml present. Also seen: mentions subagents; mentions Claude Code; mentions Codex.

Part of the promptkitty plugin — 2 skills shipped together

Good fit Use it to create project instruction files or subagent profiles for Codex, Claude Code, Grok Build, GitHub Copilot, OpenCode, Cursor, and other listed providers.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/baldaworks/promptkitty/author-agent-instructions
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 baldaworks/promptkitty --skill author-agent-instructions
Clone the repo
git clone --depth 1 https://github.com/baldaworks/promptkitty

Made for: Claude Code, Codex.

Or install promptkitty, the plugin that ships this one along with the rest of its 2 skills.

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 author-agent-instructions

README.md
[![agentmods](https://agentmods.dev/badge/skills/baldaworks/promptkitty/author-agent-instructions/github.svg)](https://agentmods.dev/skills/baldaworks/promptkitty/author-agent-instructions)
Your own site
<a href="https://agentmods.dev/skills/baldaworks/promptkitty/author-agent-instructions"><img src="https://agentmods.dev/badge/skills/baldaworks/promptkitty/author-agent-instructions/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 author-agent-instructions

Your own site · 80×15
<a href="https://agentmods.dev/skills/baldaworks/promptkitty/author-agent-instructions"><img src="https://agentmods.dev/badge/skills/baldaworks/promptkitty/author-agent-instructions.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 75 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 878 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 98% 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 $0.00075 $0.00878
Opus 5 $0.00037 $0.00439
Sonnet 5 $0.00015 $0.00176
Haiku 4.5 $0.00007 $0.00088

Measured 9d ago against content hash 5c7b8d713e1c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

author-agent-instructions 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.

Origin

This is a copy

98% identical to promptkitty-author-agent-instructions — 2 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.

plugins/promptkitty/skills/author-agent-instructions/SKILL.md · 73 lines

How it starts

The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.

PromptKitty Author Agent Instructions

Use promptkitty when installed. Otherwise use the pinned fallback npx --yes @baldaworks/[email protected] for every PromptKitty command. Use only the public CLI and remain offline after the package is available.

Read references/provider-targets.md completely before planning or writing provider files. Its current paths and schemas override stale platform paths in the pinned PromptKit template.

Obtain source material

Accept a PromptKitty Assemble handoff containing final source Markdown and its resolved template metadata. If it is absent, load PromptKitty Assemble (assemble or promptkitty-assemble) in source-only mode and describe the reusable behavior the user wants. Do not accept unresolved template parameters.

The source Markdown is authoritative for persona identity, protocols, behaviors, and output expectations. Do not execute its task.

Collect authoring choices

Resolve these values from the handoff or ask for them:

  • output type: instructions for persistent project guidance or agent for a subagent profile
  • providers: any subset of Codex, Claude Code, Grok Build, GitHub Copilot, OpenCode, and Cursor, including All
  • lowercase kebab-case slug
  • target project root, defaulting to the current repository only after confirmation
  • optional project context, path scope, model, tools, or permissions

Do not invent optional model, tool, permission, or path-scope settings. Omit them unless the user supplies them.

Assemble the authoring specification

Inspect author-agent-instructions and resolve every declared parameter:

promptkitty show "author-agent-instructions" --json

Set:

  • platform to the selected provider names
  • output_type to instructions or agent
  • base_persona from the resolved source template persona
  • selected_protocols from the resolved source components
  • behaviors to the complete assembled source Markdown via --param-file
  • scope to project
  • context to the confirmed project context plus a statement that the assembled source is complete and external PromptKit files must not be read

Read the full file on GitHub · 73 lines

Files

What ships with it

2 files 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. 9d ago First seen · 73 lines · 75 tokens per session scan A 5c7b8d713e1c

Subscribe to this mod's changes

author-agent-instructions is a skill published in the GitHub repository baldaworks/promptkitty (5 stars, last pushed 1mo ago), licensed MIT. It adds 75 tokens to every session and 878 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. It is 98% identical to promptkitty-author-agent-instructions, differing in 2 lines, and is treated as a copy.