planning

A set of project rules for planning and carrying out code changes in stages. It requires a short plan, organized edits, validation, and updates to related documentation.

In plain words
What is it for?
Use it to plan non-trivial coding tasks, group file changes, record design decisions, build a complete thin slice, and check the result with tests or smoke checks.
Why use it?
It helps prevent broad, unfinished changes and keeps code, tests, contracts, and documentation in step. It also clarifies when work should move from one project phase to the next.

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/coeusyk/inference-x/planning
Clone the repo
git clone --depth 1 https://github.com/coeusyk/inference-x

Made for: Cursor.

Per session 219 This file is loaded in full into every session.
When invoked 219 The same file — it is already loaded in full.
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 $0.00219 $0.00219
Opus 5 $0.00110 $0.00110
Sonnet 5 $0.00044 $0.00044
Haiku 4.5 $0.00022 $0.00022

Measured yesterday against content hash d78c127c7add, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

planning 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 yesterday.

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/planning.mdc · 24 lines

What it actually says

Planning rules

  • For any task beyond a small localized edit, write a short execution plan first.
  • The plan must include: goal, affected files, ordered steps, and validation approach.
  • Group edits by concern: schemas, services, routes, tests, docs.
  • Complete one concern before moving to the next when possible.
  • If a task touches contracts, docs and tests must be updated in the same work batch.
  • Prefer finishing a thin vertical slice over partially scaffolding many modules.

Phase discipline

  • Follow docs/PHASES.md as the default execution order.
  • Do not start a later phase before the current phase exit criteria are met unless explicitly instructed.
  • Record architectural changes in docs/DECISIONS.md when a non-obvious design choice is made.

Implementation rhythm

  1. Read relevant architecture and phase docs.
  2. Restate the task in repo terms.
  3. Propose the file-level plan.
  4. Implement in small steps.
  5. Validate with tests or smoke checks.
  6. Update docs affected by the change.
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. yesterday First seen · 24 lines · 219 tokens per session scan A d78c127c7add

Subscribe to this mod's changes

planning is a cursor rule published in the GitHub repository coeusyk/inference-x (2 stars, last pushed 21d ago), licensed MIT. It adds 219 tokens to every session, about $0.0011 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.