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/yonatangross/orchestkitWrote 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/yonatangross/orchestkit/sections)<a href="https://agentmods.dev/rules/yonatangross/orchestkit/sections"><img src="https://agentmods.dev/badge/rules/yonatangross/orchestkit/sections/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/yonatangross/orchestkit/sections"><img src="https://agentmods.dev/badge/rules/yonatangross/orchestkit/sections.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 | $0.00017 | $0.00582 |
| Opus 5 | $0.00009 | $0.00291 |
| Sonnet 5 | $0.00003 | $0.00116 |
| Haiku 4.5 | $0.00002 | $0.00058 |
Grade A, and why
sections 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 3d 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 — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Rule Categories
1. Verification (verification) — CRITICAL — 1 rule
Cross-cutting evidence requirements for all skill completion claims.
verification-gate.md— 5-step evidence gate: identify, run, read, verify, claim
2. Communication (communication) — HIGH — 1 rule
Anti-sycophancy and direct communication standards for review and feedback skills.
anti-sycophancy.md— Ban performative agreement, require direct technical statements
3. Adversarial Verification (adversarial) — HIGH — 1 rule
Blind-refuter protocol for evaluative skills (assess, review-pr, audit-full) — removes self-preferential bias by verifying decision-bearing findings with a separate, blind agent.
adversarial-refutation.md— Blindness contract, independent-score-first, citation-verify, quorum, no-auto-flip
4. Untrusted Input (security) — HIGH — 1 rule
Prompt-injection defense for skills that read untrusted GitHub/CI content (ci-sentinel, fix-issue, review-pr) — separate the agent that reads untrusted text from the one that acts.
untrusted-input-quarantine.md— reader/actor split, structured-facts contract, per-skill bindings
5. Playground Visual Quality (playground) — HIGH — 1 rule
Falsifiable design standard for the visual playgrounds OrchestKit emits (create-pr gate,
visualize-plan) — device-mockup user-story players and drag-and-drop decision boards. Exemplars
live in ../assets/playground-exemplars/.
playground-visual-standard.md— §0 archetype routing, HSL tokens, glass do/don't, motion budget, drag-and-drop accessibility, RTL, anti-generic checklist
6. Chart Encoding (visualization) — HIGH — 1 rule
Defers the DATA-MARK layer of every ork chart (playground, dashboard, infographic, MCP visual,
multi-surface) to CC's bundled /dataviz skill — form heuristic, six-check color formula, and the
runnable palette validator. ork owns the domain + chrome; /dataviz owns the marks. Capability-gated:
absent or FAIL → ASCII-card fallback, never a hard require.
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.
- 3d ago First seen · 52 lines · 17 tokens per session scan A 43468f28bc24
sections is a cursor rule published in the GitHub repository yonatangross/orchestkit (264 stars, last pushed today), licensed MIT. It adds 17 tokens to every session and 582 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 2026-09-09.
Other cursor rules, from other repositories
pn-tool-risk-policy
MCP tool risk tiers, HITL gates, and when to use approvalcheckpoint and gatelogappend. Use for safety reviews and workflow audits.
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.