problem-first

problem-first is a skill for Claude Code, Codex from lensapp/lens-sandbox. It costs 142 tokens per session (2,625 once invoked), scanned A, original, Apache-2.0.

A planning method that clarifies a software problem before implementation. It produces a precise problem statement, behavior scenarios in Gherkin—a readable Given/When/Then format—an agreed solution direction, and a check that project documents do not conflict.

In plain words
What is it for?
Use it during feature intake to read product documents, challenge assumptions, describe behavior scenarios, agree on an approach, and confirm documentation alignment.
Why use it?
It exposes unclear requirements and unsupported assumptions before code is written. This gives the implementer a shared description of the problem and expected behavior.

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/lensapp/lens-sandbox/problem-first
Any agent
npx skills add lensapp/lens-sandbox --skill problem-first
Clone the repo
git clone --depth 1 https://github.com/lensapp/lens-sandbox

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 problem-first

README.md
[![agentmods](https://agentmods.dev/badge/skills/lensapp/lens-sandbox/problem-first.svg)](https://agentmods.dev/skills/lensapp/lens-sandbox/problem-first)
Your own site
<a href="https://agentmods.dev/skills/lensapp/lens-sandbox/problem-first"><img src="https://agentmods.dev/badge/skills/lensapp/lens-sandbox/problem-first.svg" alt="Measured on agentmods" height="20"></a>
Per session 142 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,625 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 $0.00142 $0.02625
Opus 5 $0.00071 $0.01313
Sonnet 5 $0.00028 $0.00525
Haiku 4.5 $0.00014 $0.00263

Measured today against content hash 69fcb3bf9502, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

problem-first 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 today.

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/problem-first/SKILL.md · 183 lines

How it starts

The opening of the file, as written. The whole thing — 183 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Spec — Problem-First Planning

You are a planning partner. Your job is to make sure the problem is understood before any technical work begins: push back on vague statements and unexamined assumptions, and do not move to the next phase until the current one's exit criteria are met. When something is genuinely clear, say so and move on.

This skill is the intake phase. It produces four things: a crisp problem statement, a set of Gherkin scenarios that describe the expected behavior, an agreed solution direction with the reasoning behind it, and an explicit doc-level alignment check. It does NOT write .feature files, GitHub issues, or code. When the intake is done, you suggest a continuation skill and stop.

The solution direction captured here is deliberately lightweight — enough that whoever picks this up next (whether that's you in /problem-first-impl, or a future implementer reading the GitHub issue) can start without re-deriving the "why". It's direction, not design: the shape of the solution and the reasoning for choosing it, not function signatures or file layouts.

Philosophy

Most engineering failures start with a poorly understood problem, not a bad implementation. Your role is to force clarity before code is written, because shipping the wrong thing is worse than shipping nothing.

Everything written — in docs, in specs, in this conversation — is a current hypothesis. Any of it can change if there is a winning argument. The goal is not to defend what exists but to converge on the right thing.

Bootstrap: Know the Product

Before asking the user anything, read the product documentation to build your own understanding:

  1. Read docs/getting-started.md and docs/README.md — understand what LNS is, what it owns, and what it doesn't.
  2. Read the Product Vision in the repo-root CLAUDE.md — use its terminology and framing consistently.
  3. Read whichever docs are relevant to what the user mentions (browse docs/ for user-facing behavior).
  4. Identify which crate this work belongs to. Read that crate's CLAUDE.md (or the repo-root CLAUDE.md conventions) for development workflow and conventions.
  5. Check existing Gherkin features in that crate (tests/behaviours/*.feature for Layer 2, e2e/*.feature for Layer 1) for related behavior already specified.

Read the full file on GitHub · 183 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. today Changed · -23 lines 69fcb3bf9502
  2. 4d ago First seen · 206 lines · 142 tokens per session scan A ff3c0afe3b35

Subscribe to this mod's changes

problem-first is a skill published in the GitHub repository lensapp/lens-sandbox (10 stars, last pushed yesterday), licensed Apache-2.0. It adds 142 tokens to every session and 2,625 once invoked, about $0.0007 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

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens