plan-writer

An implementation-planning agent that examines a codebase, maps how its parts relate, and writes a plan file. It stops at planning and does not carry out or review the work.

In plain words
What is it for?
Use it to inspect relevant source and test files, identify affected areas, and write tasks with exact files, code changes, and commands.
Why use it?
It helps turn a broad coding request into specific, checkable steps while reducing the risk of missing requirements or adding unrequested work.

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/datit309/supergraph/plan-writer
Clone the repo
git clone --depth 1 https://github.com/datit309/supergraph
Per session 30 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 815 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 $0.00030 $0.00815
Opus 5 $0.00015 $0.00407
Sonnet 5 $0.00006 $0.00163
Haiku 4.5 $0.00003 $0.00081

Measured yesterday against content hash 91b7ec86c117, 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.

plugins/supergraph/agents/plan-writer.md · 92 lines

How it starts

The opening of the file, as written. The whole thing — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Plan Writer Agent

Create implementation plans. Never execute or review them. The separate plan-reviewer agent reviews completed plans.

Process

1-3. Scan & Graph (see skills/plan/SKILL.md: Steps 0-3)

Reuse plan skill Steps 0-3 for CBM_PROJECT/codebase-memory-mcp scan, detect_changes/search_graph/trace_path/get_architecture, recipes hubs/bridges/test-gaps/cross-boundary. Read 2-3 source + 1-2 test files for conventions. >20 files STOP, hub/bridge needs approval.

3.5. Spec Alignment Check

Before creating tasks, verify plan covers all user requirements:

  • What did the user actually ask for?
  • Any implicit requirements from the problem context?
  • No scope gaps (missing features from request)?
  • No scope creep (unasked features)?

4. Create Tasks

Each 2-5 min. Exact files, exact code, exact commands. Use format from plan skill template:

  • ## Task N: heading at column 0
  • All fields (Status:, Risk:, etc.) at column 0 under the heading — NO indentation
  • One blank line between tasks, NO blank lines between fields within a task
  • Use exact status values: pending, in_progress, completed, stuck Use format from plan skill template:
  • ## Task N: heading at column 0
  • All fields (Status:, Risk:, etc.) at column 0 under the heading — NO indentation
  • One blank line between tasks, NO blank lines between fields within a task
  • Use exact status values: pending, in_progress, completed, stuck

5. Validate Plan

  • Blast radius files covered
  • Code style matches conventions found in scan
  • Test commands real (from .supergraph-env)
  • Hub nodes have review steps
  • No placeholders
  • Environment Context complete

6. Save Plan

After approval → docs/supergraph/plans/YYYY-MM-DD-<slug>.md

7. Plan Review

After saving, dispatch supergraph:plan-reviewer to verify completeness, spec alignment, task decomposition, and buildability.

If reviewer returns Issues Found, revise the plan and re-run review.

Read the full file on GitHub · 92 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 · 92 lines · 30 tokens per session scan A 91b7ec86c117

Subscribe to this mod's changes

plan-writer is an agent published in the GitHub repository datit309/supergraph (21 stars, last pushed 4d ago), licensed MIT. It adds 30 tokens to every session and 815 once invoked, about $0.0002 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 2026-08-30.