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/robertsfeir/atelier-pipelineWrote 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/rules/robertsfeir/atelier-pipeline/xml-prompt-schema)<a href="https://agentmods.dev/rules/robertsfeir/atelier-pipeline/xml-prompt-schema"><img src="https://agentmods.dev/badge/rules/robertsfeir/atelier-pipeline/xml-prompt-schema/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/rules/robertsfeir/atelier-pipeline/xml-prompt-schema"><img src="https://agentmods.dev/badge/rules/robertsfeir/atelier-pipeline/xml-prompt-schema.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 | $0.03002 | $0.03002 |
| Opus 5 | $0.01501 | $0.01501 |
| Sonnet 5 | $0.00600 | $0.00600 |
| Haiku 4.5 | $0.00300 | $0.00300 |
Grade A, and why
xml-prompt-schema 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.
How it starts
The opening of the file, as written. The whole thing — 260 lines — stays where its author put it; the contents beside it link to each section on GitHub.
XML Prompt Tag Vocabulary
This document defines every XML tag used in atelier-pipeline agent persona files, skill command files, invocation prompts, and shared references. No ad-hoc tags -- if a tag is not listed here, it should not appear in any pipeline file.
Persona File Tags
Agent persona files (.cursor/agents/*.md) use these 7 tags in this order.
<identity> is always first, <output> is always last.
| Tag | Purpose | Attributes |
|---|---|---|
<identity> |
Who the agent is, role, pronouns, model | None |
<required-actions> |
Cognitive directive + proactive behaviors (numbered list) | None |
<workflow> |
Ordered steps for the agent's main work | None |
<examples> |
2-3 short scenarios showing the agent doing its job correctly | None |
<tools> |
Tool access list and tool-specific guidance | None |
<constraints> |
Boundaries and forbidden actions | None |
<output> |
Output format templates, DoR/DoD structure, handoff messages | None |
Tag ordering: <identity> first, then <required-actions>, <workflow>,
<examples>, <tools>, <constraints>, <output> last. This order
ensures the agent reads its identity and required-actions before workflow,
sees examples of correct work before encountering boundaries, and knows
its output format last.
Skill Command Tags
Skill command files (.cursor/commands/*.md) use a slightly different
structure for conversational agents running in the main thread.
| Tag | Purpose | Attributes |
|---|---|---|
<identity> |
Who the skill agent is, voice, personality | None |
<required-actions> |
Cognitive directive (no numbered steps for skills) | None |
<required-reading> |
Files to read at start of every invocation | None |
<behavior> |
How the skill operates -- question flow, modes, phases | None |
<output> |
Output format, where to save, handoff message | None |
<constraints> |
Boundaries and forbidden actions | None |
Invocation Prompt Tags
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 · 260 lines · 3,002 tokens per session scan A c8b7d1121f6f
xml-prompt-schema is a cursor rule published in the GitHub repository robertsfeir/atelier-pipeline (25 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 3,002 tokens to every session, about $0.0150 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.
Other cursor rules, from other repositories
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
cli-error-handling
CLI command error handling patterns.
prefer-direct-imports-over-module-mocks
Prefer extracting a testable core over vi.mock / vi.resetModules when unit tests need to reach production logic entangled with config, env, or singletons.
control-plane-descriptors
Control plane descriptor and instance implementation patterns.