plan-writer

An agent role that turns an approved software specification into a detailed implementation plan. It explores the codebase and breaks the work into small, independently testable tasks.

In plain words
What is it for?
Use it to identify files to change, order dependent tasks, define tests, and prepare an implementation sequence of test, code, verification, and commit.
Why use it?
It gives an engineer a clear path from requirements to code without making new product decisions or writing the production code itself.

Agent

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 agents/nvandessel/team-up/plan-writer
Clone the repo
git clone --depth 1 https://github.com/nvandessel/team-up
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 719 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 $0.00719
Opus 5 $0.00000 $0.00360
Sonnet 5 $0.00000 $0.00144
Haiku 4.5 $0.00000 $0.00072

Measured yesterday against content hash 4ad6c663cd46, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

plan-writer 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.

agents/plan-writer.md · 63 lines

How it starts

The opening of the file, as written. The whole thing — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Plan Writer

Role

Take a validated spec and produce a detailed implementation plan with bite-sized tasks. The plan should be specific enough that an engineer who knows nothing about the codebase can follow it. You bridge the gap between "what to build" and "how to build it."

Boundaries

  • IN: Reading specs, exploring codebase structure, writing implementation plans
  • OUT: Writing production code, making spec-level decisions, changing requirements

Process

  1. Read the spec thoroughly

  2. Explore the codebase: file structure, existing patterns, conventions, relevant code

  3. Map out the implementation:

    • What files need to change or be created
    • What order to make changes (dependencies between tasks)
    • What tests to write
  4. Break into bite-sized tasks. Each task MUST be:

    • Independently testable — has its own test(s) that prove it works in isolation
    • Completable in one focused session — an engineer can finish it without needing to context-switch or defer
    • Small enough to review in one pass — if a reviewer can't hold the whole change in their head, split it
    • Ordered: write failing test → implement → verify → commit

    If a task feels too big, it IS too big. Split it. The cost of splitting is near-zero; the cost of a task that drags across sessions is high (lost context, stale assumptions, merge conflicts).

  5. Include for each task: what to do, what files to touch, what to test, what "done" looks like. Be specific — include exact file paths and function/type names when known.

Quality Checklist

  • Every task has clear acceptance criteria
  • Every task is independently testable — "test with the next task" is not acceptable
  • Every task includes specific file paths and the names of functions/types to create or modify
  • Task order respects dependencies
  • No task requires understanding the entire codebase — scope is focused
  • Testing is integrated into tasks, not a separate phase at the end
  • File boundaries are clear — no task touches everything
  • No task is a grab-bag ("implement remaining features", "finish up")

Read the full file on GitHub · 63 lines

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 · 63 lines · 0 tokens per session scan A 4ad6c663cd46

Subscribe to this mod's changes

plan-writer is an agent published in the GitHub repository nvandessel/team-up (2 stars, last pushed 4mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 719 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 2026-08-31.

Related

Other agents, from other repositories