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/verdikta/verdikta-applicationsWrote 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/verdikta/verdikta-applications/verdikta-manifest)<a href="https://agentmods.dev/rules/verdikta/verdikta-applications/verdikta-manifest"><img src="https://agentmods.dev/badge/rules/verdikta/verdikta-applications/verdikta-manifest/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/verdikta/verdikta-applications/verdikta-manifest"><img src="https://agentmods.dev/badge/rules/verdikta/verdikta-applications/verdikta-manifest.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 | $0.00010 | $0.01585 |
| Opus 5 | $0.00005 | $0.00792 |
| Sonnet 5 | $0.00002 | $0.00317 |
| Haiku 4.5 | $0.00001 | $0.00159 |
Grade A, and why
verdikta-manifest 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 11d 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 — 284 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Verdikta Manifest Specification
Required Reading
Official specification: https://docs.verdikta.com/verdikta-common/MANIFEST_SPECIFICATION/
Archive Structure
Primary Archive (Evaluation Instructions)
primary-archive.zip
├── manifest.json
└── primary_query.json
manifest.json:
{
"version": "1.0",
"name": "Job Title - Evaluation for Payment Release",
"primary": {
"filename": "primary_query.json"
},
"juryParameters": {
"NUMBER_OF_OUTCOMES": 2,
"AI_NODES": [
{
"AI_MODEL": "gpt-4o",
"AI_PROVIDER": "OpenAI",
"NO_COUNTS": 1,
"WEIGHT": 0.5
}
],
"ITERATIONS": 1
},
"additional": [
{
"name": "gradingRubric",
"type": "ipfs/cid",
"hash": "QmXXX...",
"description": "Evaluation rubric"
}
],
"bCIDs": {
"submittedWork": "QmYYY..."
}
}
primary_query.json:
{
"query": "WORK PRODUCT EVALUATION REQUEST...",
"references": ["gradingRubric"],
"outcomes": ["DONT_FUND", "FUND"]
}
Hunter Archive (Work Submission)
hunter-archive.zip
├── manifest.json
├── primary_query.json
└── submission/
├── file1.txt
├── file2.pdf
└── chart.jpg
manifest.json:
{
"version": "1.0",
"name": "submittedWork",
"primary": {
"filename": "primary_query.json"
},
"additional": [
{
"name": "submitted-work-1",
"type": "text/plain",
"filename": "submission/file1.txt",
"description": "Main document with findings"
},
{
"name": "submitted-work-2",
"type": "application/pdf",
"filename": "submission/file2.pdf",
"description": "Supporting research data"
},
{
"name": "submitted-work-3",
"type": "image/jpeg",
"filename": "submission/chart.jpg",
"description": "Data visualization chart"
}
]
}
primary_query.json:
{
"query": "Custom hunter narrative explaining their submission...",
"references": ["submitted-work-1", "submitted-work-2", "submitted-work-3"]
}
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.
- 11d ago First seen · 284 lines · 10 tokens per session scan A 8e6d46a34cac
verdikta-manifest is a cursor rule published in the GitHub repository verdikta/verdikta-applications (24 stars, last pushed today), licensed MIT. It adds 10 tokens to every session and 1,585 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.
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.