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.
npx skills add baldaworks/promptkitty --skill author-agent-instructionsgit clone --depth 1 https://github.com/baldaworks/promptkittyWrote 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/skills/baldaworks/promptkitty/author-agent-instructions)<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.
<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>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 | $0.00075 | $0.00878 |
| Opus 5 | $0.00037 | $0.00439 |
| Sonnet 5 | $0.00015 | $0.00176 |
| Haiku 4.5 | $0.00007 | $0.00088 |
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.
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.
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:
instructionsfor persistent project guidance oragentfor 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:
platformto the selected provider namesoutput_typetoinstructionsoragentbase_personafrom the resolved source template personaselected_protocolsfrom the resolved source componentsbehaviorsto the complete assembled source Markdown via--param-filescopetoprojectcontextto the confirmed project context plus a statement that the assembled source is complete and external PromptKit files must not be read
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.
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 First seen · 73 lines · 75 tokens per session scan A 5c7b8d713e1c
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.
Other skills, from other repositories
lx
Codebase exploration tool that reads many files or whole directories in a single call, with per-file headers, glob include/exclude filters, function/type skeleton extraction (signatures only, no bodies), and head/tail line slicing.
dd-code-generation
Use pup CLI for immediate Datadog operations or generate code for integration into applications.
voiden
Create and edit Voiden .void files for API testing. Covers the .void file format and all enabled extension block types.
write-zot-themes
Help the user create, install, or package zot themes, including theme-only extensions.
bubbletea-testing
Use this skill whenever writing tests for Bubble Tea (charmbracelet/bubbletea) TUI applications in Go. Triggers include any mention of testing Bubble Tea models, teatest, golden file testing for TUIs, testing tea.Cmd or tea.Msg, snapshot testing terminal output, or writing tests for any Go CLI/TUI that uses the Elm…
pi-loop-forensics
Diagnose pi-go agent loops and degenerate turns — "agent loop aborted", runaway thinking with no tool calls, repeated phrases. Discriminates genuine model repetition collapse from a race, a tool-parse failure, or a too-low guard, and A/B replays a seed session across providers.