planning-workflow

planning-workflow is a cursor rule for Cursor from boparaiamrit/skills-by-amrit. It costs 14 tokens per session (497 once invoked), scanned A, original, MIT.

A set of rules for planning and implementing significant software changes. It covers code research, planning, incremental edits, tests, and build verification.

In plain words
What is it for?
Use it for feature work or other substantial changes. It guides file discovery, dependency checks, edge-case planning, implementation, testing, and final verification.
Why use it?
It helps developers understand existing code before changing it and catch mistakes while the work is still in progress.

Cursor rule for Cursor

Written for Cursor: a Cursor rule (.mdc).

Good fit Use it for feature work or other substantial changes. It guides file discovery, dependency checks, edge-case planning, implementation, testing, and final verification.

Compare 6 cursor rules from other repositories ↓
Install with agentmods
npx agentmods add rules/boparaiamrit/skills-by-amrit/planning-workflow
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.

Clone the repo
git clone --depth 1 https://github.com/boparaiamrit/skills-by-amrit

Made for: Cursor.

Wrote 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.

agentmods badge for planning-workflow

README.md
[![agentmods](https://agentmods.dev/badge/rules/boparaiamrit/skills-by-amrit/planning-workflow/github.svg)](https://agentmods.dev/rules/boparaiamrit/skills-by-amrit/planning-workflow)
Your own site
<a href="https://agentmods.dev/rules/boparaiamrit/skills-by-amrit/planning-workflow"><img src="https://agentmods.dev/badge/rules/boparaiamrit/skills-by-amrit/planning-workflow/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.

agentmods 80×15 button for planning-workflow

Your own site · 80×15
<a href="https://agentmods.dev/rules/boparaiamrit/skills-by-amrit/planning-workflow"><img src="https://agentmods.dev/badge/rules/boparaiamrit/skills-by-amrit/planning-workflow.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 14 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 497 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00014 $0.00497
Opus 5 $0.00007 $0.00249
Sonnet 5 $0.00003 $0.00099
Haiku 4.5 $0.00001 $0.00050

Measured 9d ago against content hash 0b9fc704c2cc, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

planning-workflow 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 9d 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/planning-workflow.mdc · 50 lines

What it actually says

Planning & Implementation Workflow

When implementing a feature or making a significant change, follow this structured workflow:

Phase 1: Research (Before Writing Code)

  1. Map the affected area — Find all files related to the change
  2. Understand patterns — How does existing code handle similar cases?
  3. Identify dependencies — What imports/exports are involved?
  4. Check tests — What existing tests cover this area?
  5. Read recent history — What changed recently? (git log --oneline -15)

Phase 2: Plan

  1. List all files that need to be created or modified
  2. Define the changes for each file (specific, not vague)
  3. Identify edge cases — Null values, empty arrays, max values, concurrent access
  4. Estimate risk — What could go wrong?
  5. Define verification — How will we know this works?

Phase 3: Implement

  1. One file at a time — Complete each file before moving to the next
  2. Match patterns — Follow existing codebase conventions
  3. Verify incrementally — Check that each change compiles
  4. Write tests alongside code — Don't save all tests for the end

Phase 4: Verify

  1. Build passesnpm run build
  2. All tests passnpm test (not just new tests)
  3. Lint passesnpm run lint
  4. Types passnpx tsc --noEmit
  5. No regressions — Existing features still work

Phase 5: Review

  1. Self-review the diff — Read your own changes critically
  2. Check for code smells — God functions, duplicate logic, magic numbers
  3. Verify completeness — Did you address ALL requirements?
  4. Check security — Input validation, auth checks, data exposure

Project State

If a .planning/ directory exists:

  • Read STATE.md for current context
  • Update STATE.md after completing work
  • Save plans to .planning/plans/
  • Save research to .planning/research/
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. 9d ago First seen · 50 lines · 14 tokens per session scan A 0b9fc704c2cc

Subscribe to this mod's changes

planning-workflow is a cursor rule published in the GitHub repository boparaiamrit/skills-by-amrit (5 stars, last pushed 5mo ago), licensed MIT. It adds 14 tokens to every session and 497 once invoked, about $0.0001 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.