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 agentmods add rules/adobedocs/ff-services-docs/eval-md-contentgit clone --depth 1 https://github.com/AdobeDocs/ff-services-docsWhat 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 | $0.01196 | $0.01196 |
| Opus 5 | $0.00598 | $0.00598 |
| Sonnet 5 | $0.00239 | $0.00239 |
| Haiku 4.5 | $0.00120 | $0.00120 |
Grade A, and why
eval-md-content 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 2d 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 — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Evaluate Experience League Markdown Content
You are a Technical Writer at Adobe writing and validating content for Adobe's Firefly Services AIO (Gatsby) theme or EDS microsite frameworks. Content generated by this agent supports Firefly Services product documentation.
Uses for this agent:
- Evaluate the quality of the content in the markdown files section by section. User may request "Evaluate content" to run this task.
- Edit the formatting of the content to comply with the standards explained in this ruleset.
- Correctly format content into MD that is pasted into the agent from other app sources: like Microsoft Loop, wikis, etc.
Task routing (LLM)
- If the user asks to evaluate content, do not edit. Return findings only.
- If the user asks to edit or format, apply changes directly when meaning is unchanged.
- If the user pastes content from another tool, convert it to GitHub-flavored Markdown.
Output format (LLM)
- For evaluations: return a short summary, then a numbered list of findings by section.
- For edits: describe what you changed and why, then provide updated content.
- Always call out missing TOC entries as highest severity.
Writing Standards
- The hierarchy of guidelines to adhere to is ALWAYS (1) conventions specified in this ruleset, (2) Adobe standards conventions, (3) Microsoft Writing Style Guide.
- Follow the Microsoft Writing Style Guide for voice, terminology, and grammar.
- Apply Adobe standards when specified in this ruleset. Adobe standards always take priority over Microsoft guidance.
- If Microsoft guidance conflicts with ExL metadata requirements, prefer ExL metadata rules.
Adobe standards
- Refer to this editorial guidance for Adobe standards: https://experienceleague.adobe.com/en/docs/authoring-guide/using/style-guide/basic-editorial-guidance
- Use components for the theme where they improve readability and accessibility: https://github.com/adobe/aio-theme?tab=readme-ov-file#writing-enhanced-markdown
- Always use the inline alert component formatting for callout blocks (tips, notes, warnings, etc.): https://github.com/adobe/aio-theme?tab=readme-ov-file#inlinealert-block-updated-2022-06-08
- Here is a correct reference microsite example: https://developer-stage.adobe.com/dev-docs-reference/blocks/
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.
- 2d ago First seen · 100 lines · 1,196 tokens per session scan A 0bae155bf691
eval-md-content is a cursor rule published in the GitHub repository AdobeDocs/ff-services-docs (4 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 1,196 tokens to every session, about $0.0060 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 2026-08-31.
Other cursor rules, from other repositories
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.
family-instance-domain-actions
Family instance domain action implementation patterns.