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/long-run-protocol)<a href="https://agentmods.dev/rules/yonatangross/orchestkit/long-run-protocol"><img src="https://agentmods.dev/badge/rules/yonatangross/orchestkit/long-run-protocol/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/long-run-protocol"><img src="https://agentmods.dev/badge/rules/yonatangross/orchestkit/long-run-protocol.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 | $0.00031 | $0.00974 |
| Opus 5.5 | $0.00012 | $0.00390 |
| Sonnet 5.5 | $0.00006 | $0.00195 |
| Haiku 4.5 | $0.00003 | $0.00097 |
Grade A, and why
long-run-protocol 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 8d 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 — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Long-Run Protocol
Source: Anthropic, "Getting the most out of Opus 5.5" (claude.dev/blog/getting-the-most-out-of-opus-5-5), read 2026-09-22. Quoted lines below are verbatim.
1. Name the finish line before starting
"Name the finish line, like 'the tests pass' or 'every endpoint is migrated.'" Each skill that loads this
rule states its own line as Done means: .... Work until that line is met, not until the phases are
ticked.
2. Keep going, and stop only where a human is needed
"When a step doesn't need my input, keep going. Put status notes in the same message as your next action. Stop and ask only when you can't continue without me, or before anything destructive: deleting data, force-pushing, or changing anything outside this repository."
Incorrect: ending a phase with "Want me to continue with phase 4?" when phase 4 needs no decision. Correct: a one-line status note, then the first action of phase 4, in the same message.
A skill's own AskUserQuestion gates (intent, scope, blast radius) still apply: they are decisions only
the user can make, which is the case the rule stops for. So does the end-of-run question: when the run
reaches its finish line, ask the one sign-off question from done-signoff.md (Accept done, Show me the
evidence, Not satisfied) instead of declaring the work done. Non-interactive runs return the verdict as data.
3. Keep a TASKS.md for runs that can outlive the session
"Keep a checklist in TASKS.md. Tick each item when it's done, and add anything new you find."
TaskCreate tracks the live session; a rate-limit kill or a relaunch loses it. When a run spans many
phases or several sessions, mirror the task list into TASKS.md at the worktree root and read it first
on resume. Never stage or commit it.
4. Check each subagent's evidence before accepting it
"When a subagent reports back, check its evidence before you accept it." A subagent's DONE is a claim. Accept it only when the evidence it cites is present: re-run the command, read the file and line, or open the artifact.
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.
- 8d ago Changed · +2 lines b329b96ce8f8
- 20d ago Changed · +10 lines f099c903ee7c
- 22d ago First seen · 62 lines · 31 tokens per session scan A 5a7cbd427618
long-run-protocol is a cursor rule published in the GitHub repository yonatangross/orchestkit (295 stars, last pushed today), licensed MIT. It adds 31 tokens to every session and 974 once invoked, about $0.0001 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 2026-09-24.
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.