pwn-ai-agent-promptbuilder

pwn-ai-agent-promptbuilder is a skill for Claude Code from 0dayInc/pwn. It costs 23 tokens per session (513 once invoked), scanned A, original, MIT.

A prompt-building module for an AI agent. It assembles each request's instructions from saved persona, environment, memory, and skill information.

In plain words
What is it for?
Use it when building or running PWN::AI agents whose prompts need durable state, relevant memory, and model-specific prompt-size limits.
Why use it?
It keeps information created during earlier turns available automatically and selects relevant memories instead of sending an unfiltered history. It also reduces context for smaller local models.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Good fit Use it when building or running PWN::AI agents whose prompts need durable…

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/0dayinc/pwn/prompt_builder
View source ↗ 0dayInc/pwn
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 0dayInc/pwn --skill prompt_builder
Clone the repo
git clone --depth 1 https://github.com/0dayInc/pwn

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 pwn-ai-agent-promptbuilder

README.md
[![agentmods](https://agentmods.dev/badge/skills/0dayinc/pwn/prompt_builder.svg)](https://agentmods.dev/skills/0dayinc/pwn/prompt_builder)
Your own site
<a href="https://agentmods.dev/skills/0dayinc/pwn/prompt_builder"><img src="https://agentmods.dev/badge/skills/0dayinc/pwn/prompt_builder.svg" alt="Measured on agentmods" height="20"></a>
Per session 23 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 513 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 $0.00023 $0.00513
Opus 5 $0.00012 $0.00257
Sonnet 5 $0.00005 $0.00103
Haiku 4.5 $0.00002 $0.00051

Measured 7d ago against content hash 4a868ca898b4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

pwn-ai-agent-promptbuilder 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 7d 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.

etc/default_skills/pwn/ai/agent/prompt_builder/SKILL.md · 49 lines

What it actually says

PWN::AI::Agent::PromptBuilder

Assembles the system prompt for every Loop.run invocation from durable on-disk state: PWN::Env persona, host environment probe, PWN::Memory facts, and PWN::Skills index. Re-injection IS the persistence mechanism: this is rebuilt fresh on every user turn, so a memory_remember / skill_create from the prior turn shows up here with no extra wiring. ENGINE-AWARE BUDGETING ---------------------- Local models (Ollama) drown when handed the same 6-8 KB of MEMORY / METRICS / MISTAKES / EXTROSPECTION context that a frontier model shrugs off. .budget shrinks each block for :ollama (or whatever PWN::Env[:ai][][:prompt_budget] says) so the small model spends its attention on the request, not the harness. RELEVANCE-RANKED MEMORY ----------------------- When Loop.run passes request: through, the MEMORY block is populated by PWN::MemoryIndex.recall_semantic (embedding cosine over ~/.pwn/memory.idx) instead of a recency dump — the 6 memories a small model can afford are the 6 that actually matter for THIS turn.

When to use

Call PWN::AI::Agent::PromptBuilder from pwn_eval when the task needs this module. Do not reimplement it in shell.

Methodologies

Generated from pwn/ai/agent/prompt_builder.rb. Prefer the public class methods below. Class methods take (opts = {}) and read opts.

How to call

PWN::AI::Agent::PromptBuilder.help
PWN::AI::Agent::PromptBuilder.build(opts)

Public methods

  • build
  • budget
  • authors
  • help

Source

pwn/ai/agent/prompt_builder.rb

Verification

PWN::AI::Agent::PromptBuilder.respond_to?(:build) after the module is loaded. Read the source for parameter names.

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. 7d ago First seen · 49 lines · 23 tokens per session scan A 4a868ca898b4

Subscribe to this mod's changes

pwn-ai-agent-promptbuilder is a skill published in the GitHub repository 0dayInc/pwn (78 stars, last pushed 2d ago), licensed MIT. It adds 23 tokens to every session and 513 once invoked, about $0.0001 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 2026-08-30.

Related

Other skills, from other repositories

claude-code-prompt

Reference Claude Code's prompt engineering patterns for AI/Agent development. Provides best practices for system prompts, tool design, agent orchestration, and safety.

xiufengsun/claude-code-prompt · 36 tokens

seedance-vocab-en

This skill should be used when an English Seedance 2.0 prompt is slop-heavy, generic, padded with empty quality words, tripping false-positive filters, or needs precise English production vocabulary for camera, lighting, motion, VFX, audio, and constraints.

Emily2040/seedance-2.0 · 61 tokens

ssti

Server-Side Template Injection — fingerprint the engine first (Jinja2 / Twig / Velocity / Freemarker / ERB / Smarty / Mako / Handlebars / Pug), then escalate the engine-specific primitive to RCE or sandbox escape. Use when user input is reflected through a template engine…

PentesterFlow/agent · 99 tokens

llm-router

Selects the optimal LLM model and provider for each task based on complexity, cost budget, and capability requirements. Routes cheap tasks to Haiku/GPT-4o-mini and complex tasks to Sonnet/Opus/o1. Use when deciding which model to call, optimizing LLM costs, or building multi-model agent systems. Activate on "which…

curiositech/some_claude_skills · 121 tokens

opik-optimizer

Optimize LLM prompts, tools, and agents in Opik using standardized optimizer workflows (prompt optimization, tool optimization, and parameter tuning), dataset/metric wiring, and result interpretation.

vincentkoc/dotskills · 41 tokens

seedance-prompter

A prompt-writing guide for Doubao Seedance 2.0, an AI model that generates videos from written instructions.

cclank/lanshu-awesome-ai-video-kit · 142 tokens