superspecs: Skill for Claude Code

.skills/plan-discuss/SKILL.md

plan-discuss is a skill for Claude Code, Codex from fokkerone/superspecs. It costs 48 tokens per session (1,001 once invoked), scanned A, original, MIT.

A planning interview that records decisions, assumptions, limits, and unanswered questions before a software specification is written.

In plain words
What is it for?
Reviewing relevant wiki notes, identifying useful project context, and guiding a discussion before the specification phase.
Why use it?
It brings important choices into the open early, when changing them is cheaper than during implementation.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions subagents.

This is fokkerone/superspecs's own configuration. It tells Claude Code and Codex how to work on superspecs itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything superspecs configures →

Reuse

Borrowing it

Nothing to install: this file belongs to fokkerone/superspecs. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/fokkerone/superspecs/main/.skills/plan-discuss/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/fokkerone/superspecs

Made for: Claude Code, Codex.

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 plan-discuss

README.md
[![agentmods](https://agentmods.dev/badge/skills/fokkerone/superspecs/plan-discuss/github.svg)](https://agentmods.dev/skills/fokkerone/superspecs/plan-discuss)
Your own site
<a href="https://agentmods.dev/skills/fokkerone/superspecs/plan-discuss"><img src="https://agentmods.dev/badge/skills/fokkerone/superspecs/plan-discuss/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for plan-discuss

Your own site · 80×15
<a href="https://agentmods.dev/skills/fokkerone/superspecs/plan-discuss"><img src="https://agentmods.dev/badge/skills/fokkerone/superspecs/plan-discuss.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 48 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,001 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00048 $0.01001
Opus 5 $0.00024 $0.00500
Sonnet 5 $0.00010 $0.00200
Haiku 4.5 $0.00005 $0.00100

Measured 8d ago against content hash d19bb1c4bfa4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

plan-discuss 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 8d 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.

.skills/plan-discuss/SKILL.md · 157 lines

How it starts

The opening of the file, as written. The whole thing — 157 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill: plan-discuss

You are opening the discussion phase. This happens before any spec is written.

The goal is to capture every decision, assumption, constraint, and open question so the spec that follows is grounded — not guessed.

Why this step exists

Decisions made during planning are cheap. Decisions discovered during implementation are expensive. This step makes the cheap ones explicit before they become expensive ones.

Steps

1. Orient with the wiki

Before asking anything, scan the wiki for relevant context using tiered retrieval:

Tier 1 — Index scan (always):

  • Read superspec/wiki/Home.md — domain catalog and recent ingest activity
  • Read only the frontmatter (title, tags, summary) of every page in superspec/wiki/ (skip raw/, .obsidian/)
  • Score each page for relevance to the feature being described

Tier 2 — Deep read (targeted):

  • Open the full body of the 3–5 most relevant pages
  • Follow [[wikilinks]] one level deep for directly related pages

Report before the first question:

  • List relevant pages found with a one-line summary of what each contributes
  • Flag decisions, patterns, or interfaces that should inform or constrain this discussion
  • If the wiki is empty or nothing is relevant: say so explicitly — "Wiki has no relevant pages for this feature."

2. Understand the rough idea

Ask the user to describe what they want to build. Keep it conversational. One question at a time. Cover:

What

  • What does this feature do from the user's perspective?
  • What problem does it solve?

Why now

  • What's the trigger for building this?
  • What happens if we don't build it?

Constraints

  • Technical constraints (existing stack, performance requirements, etc.)
  • Scope constraints (what's explicitly NOT included?)
  • Time or complexity constraints?

Success

  • How do we know this is done?
  • What does "working" look like?

Risks

  • What could go wrong?
  • What are we uncertain about?

Do not ask all questions at once. Read the answers and ask follow-ups. Stop when you have enough to write the discussion doc.

Read the full file on GitHub · 157 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. 8d ago First seen · 157 lines · 48 tokens per session scan A d19bb1c4bfa4

Subscribe to this mod's changes

plan-discuss is a skill published in the GitHub repository fokkerone/superspecs (4 stars, last pushed 2mo ago), licensed MIT. It adds 48 tokens to every session and 1,001 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 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens