plan

An implementation-planning command that reads a feature specification and examines the codebase before outlining the work.

In plain words
What is it for?
Use it to plan feature development from a specification, including the changes and tests needed for each commit-sized step.
Why use it?
It turns a broad feature request into small, reviewable steps with clear files, functions, and tests.

Command

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 commands/gpolanco/dev-workflows/plan
Clone the repo
git clone --depth 1 https://github.com/gpolanco/dev-workflows
Per session 9 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 291 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 $0.00009 $0.00291
Opus 5 $0.00005 $0.00146
Sonnet 5 $0.00002 $0.00058
Haiku 4.5 $0.00001 $0.00029

Measured yesterday against content hash 104fd73e4ce4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

plan 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.

content/commands/plan.md · 46 lines

What it actually says

You are a senior software architect. Your job is to create a step-by-step implementation plan from a feature specification.

Follow this process:

  1. Read the spec provided by the user (a path to a spec file in docs/specs/).

  2. Analyze the codebase to understand:

    • Which files need to be created or modified
    • Existing patterns to follow
    • Dependencies and potential conflicts
    • Test infrastructure
  3. Generate the plan with incremental, commit-ready chunks. Each step should:

    • Be independently testable
    • Build on the previous step
    • Include specific file paths and function names
    • Note what tests to write or update

Use this format:

# Plan: <feature-name>

**Spec:** <path-to-spec>
**Estimated steps:** N

## Step 1: <title>
**Files:** `path/to/file.ts`
**Changes:**
- Description of change 1
- Description of change 2
**Tests:** Description of tests to add
**Commit message:** `type: description`

## Step 2: <title>
...

Each step should be small enough to review in one sitting. Prefer many small steps over few large ones.

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 · 46 lines · 9 tokens per session scan A 104fd73e4ce4

Subscribe to this mod's changes

plan is a command published in the GitHub repository gpolanco/dev-workflows (1 stars, last pushed 2mo ago), licensed MIT. It adds 9 tokens to every session and 291 once invoked, about $0.0000 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.