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.
git clone --depth 1 https://github.com/jnPiyush/AgentXWrote 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/commands/jnpiyush/agentx/ai-agent)<a href="https://agentmods.dev/commands/jnpiyush/agentx/ai-agent"><img src="https://agentmods.dev/badge/commands/jnpiyush/agentx/ai-agent/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/commands/jnpiyush/agentx/ai-agent"><img src="https://agentmods.dev/badge/commands/jnpiyush/agentx/ai-agent.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 | $0.00020 | $0.00598 |
| Opus 5.5 | $0.00008 | $0.00239 |
| Sonnet 5.5 | $0.00004 | $0.00120 |
| Haiku 4.5 | $0.00002 | $0.00060 |
Grade A, and why
AI Agent Builder 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.
How it starts
The opening of the file, as written. The whole thing — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI Agent Builder Prompt
Context
You are building an AI agent for issue {{issue_number}}.
Before writing code, review these resources:
- AI Agent Development Skill:
.github/skills/ai-systems/ai-agent-development/SKILL.md - Architecture Decision:
docs/artifacts/adr/ADR-{{issue_number}}.md(if exists) - AI Instructions:
.github/instructions/ai.instructions.md
Instructions
1. Determine Agent Pattern
Choose the simplest pattern that solves the problem:
| Pattern | When to use |
|---|---|
| Single agent | One task, 1-3 tools, straightforward flow |
| Multi-agent | Multiple specialized roles, complex orchestration |
| Pipeline | Sequential steps with clear input/output boundaries |
2. Scaffold the Agent
For each agent, define:
- System prompt - stored in a separate
.mdor.txtfile - Tools/plugins - typed function definitions with clear descriptions
- Model configuration - deployment name, temperature, max tokens
- Error handling - retries, timeouts, fallback behavior
3. Set Up Tracing
Enable observability from day one:
- Configure OpenTelemetry tracing
- Use AI Toolkit Trace Viewer for local debugging (
Ctrl+Shift+P->AI Toolkit: Open Trace Viewer) - Log token usage and latency per call
4. Add Evaluation
Before marking the agent as complete:
- Create a test dataset (minimum 10 representative queries)
- Define quality evaluators (relevance, correctness, safety)
- Run evaluation and verify passing thresholds
5. Security Checklist
- No hardcoded credentials (use env vars or Key Vault)
- Input validation on all user-facing inputs
- Content filtering on model outputs
- Tool access scoped to minimum required permissions
Output Format
## Agent Implementation Summary
**Pattern**: [Single/Multi/Pipeline]
**Model**: [deployment name]
**Tools**: [list of tools implemented]
### Files Created
- `src/agents/[name].py` - Agent implementation
- `src/prompts/[name]-system.md` - System prompt
- `src/tools/[name].py` - Tool definitions
- `tests/test_[name].py` - Unit tests
### Evaluation Results
- Dataset: [N] queries
- Pass rate: [X]%
- Key metrics: [relevance, correctness, etc.]
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.
- 7d ago Changed 3ff072bf2dbe
- 1mo ago Changed 8e160a8d27dc
- 1mo ago First seen · 84 lines · 20 tokens per session scan A a4e57f412cda
AI Agent Builder is a command published in the GitHub repository jnPiyush/AgentX (16 stars, last pushed 3d ago), licensed Apache-2.0. It adds 20 tokens to every session and 598 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 2026-09-06.
Other commands, from other repositories
prompt
System instructions for writing effective prompts. Apply when generating commands, skills, agents, or any LLM instructions.
boot
Start a new PromptKit prompt assembly session (alias for /bootstrap).
prompt-show
Display full details of a saved prompt by ID.
music-suno-prompt
Grounded Suno prompt synthesis from local knowledge corpus + persona canon + label canon. No vibes-prompting.
ai
Load the Kaizen skill for production-ready AI agent implementation with signature-based programming and multi-agent coordination.
develop-image-prompt.eval
Generates a detailed image generation prompt from a document or content description. Good output: a prompt that is specific, visual, non-abstract, includes style/composition/lighting guidance, and is calibrated to the specified dimensions and style options.