implementation-order

A rule that orders implementation work from the lowest suitable code layer upward, following a layered “cake” model. Tests and lower-level behavior come before agent, protocol, or HTTP wiring.

In plain words
What is it for?
Follow it when adding behavior to decide where code belongs, write tests at the owning layer, and update API surfaces only after the core pieces work.
Why use it?
It prevents business logic from being duplicated in commands or HTTP handlers and reduces the chance of building on untested lower layers.

Cursor rule for Cursor

Install

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.

agentmods
npx agentmods add rules/coddy-project/coddy-agent/implementation-order
Clone the repo
git clone --depth 1 https://github.com/coddy-project/coddy-agent

Made for: Cursor.

Per session 0 Nothing until a file matches its globs; then the whole rule loads.
When invoked 254 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.00254
Opus 5 $0.00000 $0.00127
Sonnet 5 $0.00000 $0.00051
Haiku 4.5 $0.00000 $0.00025

Measured 2d ago against content hash 39942dc8699d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

implementation-order 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.

.cursor/rules/implementation-order.mdc · 26 lines

What it actually says

Implementation order

For new behavior, workflow.mdc wins on red-green order. Use this file to decide where code lives and which layer to extend first.

  1. Extend the lowest layer that can own the change with no new upward dependencies.
  2. Add tests at that layer before or with the change (see testing.mdc).
  3. Wire through internal/agent or internal/acp only after lower pieces exist and pass tests.
  4. Optional HTTP surface - last mile in external/httpserver, then refresh openapi.go and docs per api-layer.mdc and workflow.mdc.

Forbidden

  • Skipping tests for new behavior.
  • Placing domain logic in cmd/ or duplicating it in HTTP handlers instead of reusing internal/ APIs.

References

@architecture.mdc @workflow.mdc @api-layer.mdc

Changes

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.

  1. 2d ago First seen · 26 lines · 0 tokens per session scan A 39942dc8699d

Subscribe to this mod's changes

implementation-order is a cursor rule published in the GitHub repository coddy-project/coddy-agent (127 stars, last pushed 4d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 254 tokens. 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.