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/legann/repovineWrote 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/legann/repovine/repovine-subagent-orchestration)<a href="https://agentmods.dev/rules/legann/repovine/repovine-subagent-orchestration"><img src="https://agentmods.dev/badge/rules/legann/repovine/repovine-subagent-orchestration.svg" alt="Measured on agentmods" 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 | $0.00508 | $0.00508 |
| Opus 5 | $0.00254 | $0.00254 |
| Sonnet 5 | $0.00102 | $0.00102 |
| Haiku 4.5 | $0.00051 | $0.00051 |
Grade A, and why
repovine-subagent-orchestration 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.
What it actually says
repovine -- Main Agent Subagent Orchestration
You are the main agent. Project leaf subagents live in client agent dirs:
- Cursor:
.cursor/agents/*.md(@project-subagent-sample) - Claude Code:
.claude/agents/*.md(@project-subagent-sampleor "Use the project-subagent-sample subagent") - Codex:
.codex/agents/*.toml(delegate byname)
The default implementer after repovine setup is project-subagent-sample. Specialist agents are repo-owned copies of _TEMPLATE.project-subagent.*. Agent identity comes from frontmatter/TOML name, not filename.
Delegation policy:
- Non-trivial implementation: delegate to project-subagent-sample unless the user named project subagents or explicitly asked the main chat to implement.
- One named subagent: use only that agent.
- Two or more named subagents: use exactly the named set; do not add the default unless named.
- Parallel runs only for disjoint scopes; leaf subagents never call each other. Exception: never parallelize annotation writes —
repovine-annotation-writerand any agent callingwrite_annotationrun one at a time, even across disjoint module scopes, because every write goes through one debounced annotation store (parallel writers gain no throughput and can lose annotations). - Main chat stays direct for trivial edits and questions; route utility work to
repovine-repo-explorer,repovine-annotation-writer,repovine-architecture-auditor, orrepovine-code-reviewerwhen that specialist fits. - Architecture audits use
repovine-architecture-auditor; read-only implementation/diff reviews userepovine-code-reviewer.
Handoffs must include scope, acceptance criteria, contracts, prior handoff context, files/nodes touched, tests, and blockers. Run refresh_context between dependent phases after graph-relevant edits. After feature work, use repovine-workflow for post-edit verification or repovine-review for read-only review, then repovine-annotations in touched scope — Drain the annotation queue in batches until needsWork: 0 (includes propagation-stale with staleKind: "propagation").
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 First seen · 26 lines · 508 tokens per session scan A ed18c78ead35
repovine-subagent-orchestration is a cursor rule published in the GitHub repository legann/repovine (0 stars, last pushed 1mo ago), licensed MIT. It adds 508 tokens to every session, about $0.0025 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
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.