plan-em

An engineering-management planner that turns an approved PRD into an engineering plan after checking the project's architecture and shared rules.

In plain words
What is it for?
Use it to scope a PRD for engineering, run its required checks and certification, and activate approved specialist agents.
Why use it?
It coordinates technical planning and specialist selection before coding begins.

Skill for Claude CodeCodex

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 skills/ndisisnd/msg/plan-em
Any agent
npx skills add ndisisnd/msg --skill plan-em
Clone the repo
git clone --depth 1 https://github.com/ndisisnd/msg

Made for: Claude Code, Codex.

Per session 178 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,829 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 $0.00178 $0.01829
Opus 5 $0.00089 $0.00915
Sonnet 5 $0.00036 $0.00366
Haiku 4.5 $0.00018 $0.00183

Measured 2d ago against content hash fb0f5fb6f539, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

plan-em 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 2d 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.

.claude/skills/plan-em/SKILL.md · 100 lines

How it starts

The opening of the file, as written. The whole thing — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.

plan-em

This file is a router. The five-step protocol lives in refs/protocol-em.md and the team-lane fan-out in refs/protocol-team.md — neither is restated here.

Usage

Invoke: /plan-em <prd-path>. The PRD path is a .md file inside a PRD folder in any lane — features/{planned,wip,done}/prd-[n]-[slug]/ or the legacy flat features/prd-[n]-[slug]/.

  • Slash command: /plan-em · natural language: "engineering plan for ", "scope this PRD", "spin up eng agents" · context: a path to an existing approved PRD .md file, typically passed forward from plan-pm or plan-review
  • /plan-em <prd-path> --quiet / --status <n>m — suppress or retune this run's status heartbeat; flag beats policy beats default (../shared/refs/status-heartbeat.md)

Hard refusals:

  • Invocation without a PRD path: refuse. State that plan-em requires an existing PRD. Offer two paths: run /plan-pm to create one, or supply a path to an existing PRD .md file.
  • PRD path does not exist or does not match a lane-lifecycle path — features/{planned,wip,done}/prd-*/prd-*.md (top-level) or features/{planned,wip,done}/prd-*/prd-*/prd-*.md (nested sub-PRD, per plan-pm's § Sub-PRD mode) — or the legacy flat features/prd-*/prd-*.md / features/prd-*/prd-*/prd-*.md: refuse. State the expected location.

Execution mode

Two mutually exclusive execution lanes — --team is the default. The flag changes only how the wave is dispatched at Step 4; every other step is identical in both lanes.

Flag Lane Step 4 dispatch
--team (default) Team one orchestrator engineer agent on Opus decomposes the wave below the roster/stack level into file-disjoint, model-tiered packets and fans them out to leaf eng subagents.
--solo Solo one leaf eng subagent per roster stack, whole-stack scope each, on the inherited model.

In --team mode plan-em is a thin dispatcher: it spawns the orchestrator backgrounded as one watched leaf and relays its REPORT blocks; run-ids stay disjoint (emteam-<epoch> vs em-<epoch>) — mechanics in refs/protocol-em.md Step 4 + ../shared/refs/status-heartbeat.md § Relaying across a subagent boundary. The mode is a persisted preference, not just a per-run flag (refs/protocol-em.md Step 0; pref file: ../shared/refs/exec-mode-pref.md).

Read the full file on GitHub · 100 lines

Files

What ships with it

3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 2d ago First seen · 100 lines · 178 tokens per session scan A fb0f5fb6f539

Subscribe to this mod's changes

plan-em is a skill published in the GitHub repository ndisisnd/msg (6 stars, last pushed 16d ago), licensed MIT. It adds 178 tokens to every session and 1,829 once invoked, about $0.0009 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.