planning-doc-agent

planning-doc-agent is an agent for coding agents from richfrem/agent-plugins-skills. It costs 99 tokens per session (1,956 once invoked), scanned A, original, MIT.

A planning agent that drafts technical specification files, implementation plans, and task outlines from an approved discovery handoff.

In plain words
What is it for?
It is used to prepare specification, plan, and task documents, and to identify when implementation work needs another discovery cycle.
Why use it?
It helps turn discovery findings into organized engineering work when the project uses an execution framework.

Agent

Part of the exploration-cycle-plugin plugin — 20 skills, 15 agents shipped together

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/richfrem/agent-plugins-skills/planning-doc-agent
Clone the repo
git clone --depth 1 https://github.com/richfrem/agent-plugins-skills

Or install exploration-cycle-plugin, the plugin that ships this one along with the rest of its 20 skills, 15 agents.

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-doc-agent

README.md
[![agentmods](https://agentmods.dev/badge/agents/richfrem/agent-plugins-skills/planning-doc-agent.svg)](https://agentmods.dev/agents/richfrem/agent-plugins-skills/planning-doc-agent)
Your own site
<a href="https://agentmods.dev/agents/richfrem/agent-plugins-skills/planning-doc-agent"><img src="https://agentmods.dev/badge/agents/richfrem/agent-plugins-skills/planning-doc-agent.svg" alt="Measured on agentmods" height="20"></a>
Per session 99 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,956 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 $0.00099 $0.01956
Opus 5 $0.00049 $0.00978
Sonnet 5 $0.00020 $0.00391
Haiku 4.5 $0.00010 $0.00196

Measured yesterday against content hash e974e0140dcd, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

planning-doc-agent 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/exploration-cycle-plugin/agents/planning-doc-agent.md · 171 lines

How it starts

The opening of the file, as written. The whole thing — 171 lines — stays where its author put it; the contents beside it link to each section on GitHub.

⚠️ OPTIONAL — This agent is only useful when an execution harness plugin is present and the quantum double diamond framework is in use. If you are running exploration as a standalone discovery tool (no execution harness, no double diamond), skip this agent entirely — your workflow ends at exploration/handoffs/handoff-package.md.


Role in the Quantum Double Diamond Framework

The exploration cycle is Diamond 1 (Discover → Define). The Spec-Kitty engineering cycle is Diamond 2 (Develop → Deliver). This agent bridges the two — but the bridge is optional and must be explicitly enabled.

The relationship is bidirectional:

  • Exploration → Spec-Kitty: pre-draft artifacts from the handoff package to smooth the transition into the engineering cycle
  • Spec-Kitty → Exploration: when the engineering cycle uncovers unresolved ambiguity, scope and trigger a new exploration cycle (cycling back to Diamond 1)

Multiple exploration cycles may be spawned during a single engineering cycle, including:

  • During spec authoring — unclear requirements or missing business rules
  • During work package planning — unclear scope, constraints, or dependencies
  • During implementation — unknown unknowns surface that require discovery before proceeding

In all re-entry cases, exploration is not a failure mode — it is a designed feedback loop.


Invocation Modes

Mode: spec-draft

Pre-drafts spec.md from the handoff package. Output goes to staging — not directly into kitty-specs/.

pythonscripts/dispatch.py \
  --agent .agents/agents/exploration-cycle-plugin-planning-doc-agent.md \
  --context exploration/handoffs/handoff-package.md \
  --instruction "Mode: spec-draft. Pre-draft a spec.md from this exploration handoff. Follow Spec-Kitty spec format. Mark any gap with [NEEDS HUMAN INPUT]. Output to staging only." \
  --output exploration/planning-drafts/spec-draft.md

Mode: plan-draft

Pre-drafts plan.md with high-level phases and work package hints from the handoff.

Read the full file on GitHub · 171 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 · 171 lines · 99 tokens per session scan A e974e0140dcd

Subscribe to this mod's changes

planning-doc-agent is an agent published in the GitHub repository richfrem/agent-plugins-skills (6 stars, last pushed yesterday), licensed MIT. It adds 99 tokens to every session and 1,956 once invoked, about $0.0005 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 2026-09-03.