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/coddy-project/coddy-agent/architecturegit clone --depth 1 https://github.com/coddy-project/coddy-agentWhat 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 | $0.00803 | $0.00803 |
| Opus 5 | $0.00402 | $0.00402 |
| Sonnet 5 | $0.00161 | $0.00161 |
| Haiku 4.5 | $0.00080 | $0.00080 |
Grade A, and why
architecture 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 2d 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 — 42 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Architecture
Coddy is a Go CLI and ACP harness. Keep dependencies flowing inward: higher layers orchestrate lower ones; shared types stay shallow.
Rough layers (low to high)
internal/version,internal/logger, small shared helpers - minimal inward imports.internal/config- configuration structs and loading.internal/session,internal/llm,internal/prompts,internal/bgtask- runtime state, model access, and the background task pool (internal/bgtaskimports onlyinternal/platform; nothing below it may import back).internal/tools,internal/permission,internal/skills- capabilities and policies.internal/agent- ReAct-style loop assembling the above.internal/acp- ACP protocol server on top of the agent and session manager.cmd/coddy- CLI entrypoints and wiring.
Optional build tags
memory-external/memorylong-term memory copilot and HTTP session memory routes;//go:build memory. Recommended together withhttpfor/coddy/sessions/.../memory/*. Default full binary in README and Docker includesmemory.external/httpserver- OpenAI-shaped HTTP API;//go:build http. Embedded SPA uses//go:build http && uiwithexternal/ui. Keep handler registration andopenapi.goin sync.external/scheduler(daemon/,storage/,service/schedservice,tools/schedtools) - cron and related tools; scheduler tag.
Do not introduce import cycles. If a new package would cycle, split interfaces or move shared types down-layer.
Optional module tools (external/*/tools)
Optional domains that ship their own LLM-callable tools (not the main internal/tools registry) use internal/tooling.Tool: Definition (llm.ToolDefinition) plus Execute func(ctx context.Context, argsJSON string, env *tooling.Env) (string, error) in the same file, same pattern as external/scheduler/tools/job_get.go.
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.
- 2d ago First seen · 42 lines · 803 tokens per session scan A 64e710562f7d
architecture is a cursor rule published in the GitHub repository coddy-project/coddy-agent (127 stars, last pushed 4d ago), licensed MIT. It adds 803 tokens to every session, about $0.0040 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 2026-08-30.
Other cursor rules, from other repositories
agent-development
Python agents are typically in folders named agent-py/ or agent/ and use the sdk-python/ package.
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.