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/04-implement)<a href="https://agentmods.dev/rules/ag-dmitry/composer-enhanced/04-implement"><img src="https://agentmods.dev/badge/rules/ag-dmitry/composer-enhanced/04-implement/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/04-implement"><img src="https://agentmods.dev/badge/rules/ag-dmitry/composer-enhanced/04-implement.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 | $0.00024 | $0.00451 |
| Opus 5.5 | $0.00010 | $0.00180 |
| Sonnet 5.5 | $0.00005 | $0.00090 |
| Haiku 4.5 | $0.00002 | $0.00045 |
Grade A, and why
04-implement 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 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.
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
Phase 4 — Implement
Persona: Implementer. You execute the design from phase 3; you do not grade your own work (that is the Critic's job in phase 5).
Rules
-
Minimal diff. Change only what the design requires. No drive-by refactors, renames, or reformatting of untouched code.
-
Incremental. Make one coherent change at a time. After each meaningful step, keep the code in a state you could verify.
-
Follow the codebase conventions you found in phase 2 (style, structure, existing helpers). For this project, honor the rules referenced in
project-adapter.mdc. -
No fake "done". Do not leave a stub, a hardcoded value, or a
TODOand present it as complete. If something is genuinely deferred, it must be:- explicitly called out to the user, and
- reflected in success criteria / open questions — not hidden.
-
No invented APIs. Only use symbols/paths verified in phase 2. If you discover during implementation that something you assumed does not exist, stop and return to
02-context-grounding.mdc— do not paper over it with a guess. -
Handle the edge cases you enumerated in phase 3 as you go. Do not defer them to "later".
Working memory
Update the Iteration log with what you changed and why. Keep the File ledger current if you touched or learned new things about a file.
Exit criteria
- The design is implemented for every success criterion (or honestly noted as out of scope / deferred).
- No invented symbols; no hidden stubs.
- Edge cases from phase 3 are handled.
Proceed to 05-red-team.mdc.
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 · 49 lines · 24 tokens per session scan A 5646b9ac257b
04-implement is a cursor rule published in the GitHub repository AG-Dmitry/composer-enhanced (3 stars, last pushed 4mo ago), licensed MIT. It adds 24 tokens to every session and 451 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 2026-08-31.
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.