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.
npx agentmods add rules/ag-dmitry/composer-enhanced/escalation-subagentsgit clone --depth 1 https://github.com/AG-Dmitry/composer-enhancedWrote 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/ag-dmitry/composer-enhanced/escalation-subagents)<a href="https://agentmods.dev/rules/ag-dmitry/composer-enhanced/escalation-subagents"><img src="https://agentmods.dev/badge/rules/ag-dmitry/composer-enhanced/escalation-subagents.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 | $0.00026 | $0.00731 |
| Opus 5 | $0.00013 | $0.00365 |
| Sonnet 5 | $0.00005 | $0.00146 |
| Haiku 4.5 | $0.00003 | $0.00073 |
Grade A, and why
escalation-subagents 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 4d 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 — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Escalation & Subagents
Use subagents when the main model has been in the same context too long and has lost the objectivity needed to find real bugs, or when an architectural question requires deeper reasoning than the main model can reliably provide in a single pass.
When to escalate
| Trigger | Recommended subagent type |
|---|---|
| Iteration-3 checkpoint: still failing | Critic subagent (readonly) |
| Phase 03 on a high-complexity/ambiguous task | Design consultant subagent |
| Phase 05 when confidence in self-critique is low | Critic subagent (readonly) |
| Pre-submit: security/auth-sensitive change | Security critic subagent |
Do not escalate for medium tasks or as a substitute for doing the work in phases 01-05.
Critic subagent (phase 05 escalation, iteration-3 checkpoint)
Task(
description: "Critic review",
subagent_type: "generalPurpose",
readonly: true,
model: "gemini-3.1-pro",
prompt: "Review the following diff and implementation against these success
criteria: [paste from working memory].
Assume bugs exist. Hunt for: logic errors, missing nulls, unhandled
async paths, requirement drift, regressions, hidden stubs.
Return a concrete list of suspected issues (file:line + description).
Do NOT implement fixes — findings only."
)
Model selection: gemini-3.1-pro is suited for checklist-driven review at
lower cost. For security-sensitive or highly ambiguous architectural critique,
you may substitute claude-4.6-sonnet-medium-thinking.
Design consultant subagent (phase 03 optional)
Task(
description: "Design consultant",
subagent_type: "generalPurpose",
readonly: true,
model: "claude-4.6-sonnet-medium-thinking",
prompt: "Given this goal and constraints [paste from working memory], propose
and compare two architectures. Return trade-offs and a recommendation.
Do not implement — design only."
)
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.
- 4d ago First seen · 85 lines · 26 tokens per session scan A fa382721bb9a
escalation-subagents is a cursor rule published in the GitHub repository AG-Dmitry/composer-enhanced (3 stars, last pushed 2mo ago), licensed MIT. It adds 26 tokens to every session and 731 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 2026-08-31.
Other cursor rules, from other repositories
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.
family-instance-domain-actions
Family instance domain action implementation patterns.