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/SecondLifes/delphi-expertWrote 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/secondlifes/delphi-expert/analysis-output)<a href="https://agentmods.dev/rules/secondlifes/delphi-expert/analysis-output"><img src="https://agentmods.dev/badge/rules/secondlifes/delphi-expert/analysis-output/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/secondlifes/delphi-expert/analysis-output"><img src="https://agentmods.dev/badge/rules/secondlifes/delphi-expert/analysis-output.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 | $0.01449 | $0.01449 |
| Opus 5.5 | $0.00580 | $0.00580 |
| Sonnet 5.5 | $0.00290 | $0.00290 |
| Haiku 4.5 | $0.00145 | $0.00145 |
Grade A, and why
analysis-output 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 1mo 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- analysis-output — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Analysis/Evaluation/Edit Output Convention
The shared input-resolution and output-naming rule for the bundled
rad-prompt-studio skill's three master prompts
(analysis-base-prompt.md, evaluation-base-prompt.md,
edit-base-prompt.md). None of those three files restate this — they all
point here. Without this file present, none of them can resolve where a
report goes or what it is named.
Where input comes from
- A specific path is named in the request (a file or a folder) → analyze/evaluate/edit that path directly, in place. Nothing gets copied anywhere first.
- No path named, request is "review this project/repo" or
equivalent → bulk traversal mode (
analysis-base-prompt.md's "Determining the target" section). The map is this repo's ownAGENTS.md+docs/proje-haritasi.md, not a staged folder. - Request is "system analizi"/"system analysis" or equivalent →
System Analysis mode (
analysis-base-prompt.md's own section). In a kit, the system layer is.agents/skills/,.agents/rules/,.agents/commands/and the four AI-primary identity files (AGENTS.md,.claude/CLAUDE.md,.github/copilot-instructions.md,.gemini/rules/project-rules.md) — never the kit's own subject-matter code undersrc/orexamples/. Drop everything on the exclusion list (any*.tr-TR.mdfile, and any bundled third-party skill this kit did not author), then present the rest as a numbered pick-list and wait for the user to choose before analyzing anything. - No path named and no bulk-review/system-analysis phrasing either →
scan
src/for.mdfiles and skill-shaped folders (a folder containing its ownSKILL.md). Present every match as a numbered pick-list and ask the user which one(s) to analyze — never a bare open-ended "what would you like me to analyze?" when there's something concrete to offer. Only fall back to the bare open-ended question if that scan comes back empty. Never guess, and never treat "nothing specified" as "nothing to do."
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.
- 1mo ago First seen · 114 lines · 1,449 tokens per session scan A d61297700501
analysis-output is a cursor rule published in the GitHub repository SecondLifes/delphi-expert (3 stars, last pushed 1mo ago), licensed MIT. It adds 1,449 tokens to every session, about $0.0058 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 2026-09-03.
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.
prefer-assertions-over-defensive-checks
Prefer assertions over defensive checks when data is guaranteed to be valid.
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.
shared-plane-packages
Pattern for creating shared plane packages that serve both migration and runtime planes.