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/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/project-adapter)<a href="https://agentmods.dev/rules/ag-dmitry/composer-enhanced/project-adapter"><img src="https://agentmods.dev/badge/rules/ag-dmitry/composer-enhanced/project-adapter/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/ag-dmitry/composer-enhanced/project-adapter"><img src="https://agentmods.dev/badge/rules/ag-dmitry/composer-enhanced/project-adapter.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 | $0.00019 | $0.01055 |
| Opus 5.5 | $0.00008 | $0.00422 |
| Sonnet 5.5 | $0.00004 | $0.00211 |
| Haiku 4.5 | $0.00002 | $0.00105 |
Grade C, and why
project-adapter scanned grade C with 1 finding 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 2mo 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.
Hidden instructionshighPrompt injection
Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.
<!-- Example format: | Area / path pattern | Read before touching | |---|---| | src/api/** | docs/api-contracts.md | | src/components/** | docs/design-system.md | | src/stores/** | docs/state-management.md | | src/auth/* How it starts
The opening of the file, as written. The whole thing — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project Adapter
This is the only file that needs editing when adding the protocol to a new project. The core phase files (01–07, working-memory, escalation) are generic and should not need modification.
Replace every FILL_IN_* placeholder below with your project's specifics.
Delete comment lines starting with <!-- --> once filled in.
Verify commands
These commands are run by the Verifier (phase 06) and by scripts/verify.ts.
Update the GATES array in scripts/verify.ts to match if they differ from the
defaults.
# Typecheck
FILL_IN_TYPECHECK_COMMAND # e.g. pnpm typecheck | npm run tsc | yarn tsc --noEmit
# Lint
FILL_IN_LINT_COMMAND # e.g. pnpm lint | npm run lint | yarn eslint src
# Tests (CI-safe: no watch, exit on first failure is OK)
FILL_IN_TEST_COMMAND # e.g. pnpm test:ci | npm test | yarn jest --ci
Documentation & conventions to consult
List the docs or rule files the Planner should open before modifying each area. The model reads these in phase 02 (context grounding).
| Area / path pattern | Read before touching |
|---|---|
| FILL_IN_AREA_1 | FILL_IN_DOC_1 |
| FILL_IN_AREA_2 | FILL_IN_DOC_2 |
Phase 02 — Context grounding additions
Any project-specific reminders for the Planner when gathering context:
- FILL_IN_CONTEXT_NOTE_1
- FILL_IN_CONTEXT_NOTE_2
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.
- 2mo ago First seen · 154 lines · 19 tokens per session scan C c7a8016988ad
project-adapter is a cursor rule published in the GitHub repository AG-Dmitry/composer-enhanced (3 stars, last pushed 4mo ago), licensed MIT. It adds 19 tokens to every session and 1,055 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it C with 1 finding (hidden instructions). 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.
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.
config-validation-and-normalization
Config validation and normalization responsibilities (defineConfig normalizes, the orm section schema validates and resolves paths, the loader reports per-section diagnostics).
control-plane-descriptors
Control plane descriptor and instance implementation patterns.