diagnose

diagnose is a skill for Claude Code, Codex from VGrss/Acumen. It costs 47 tokens per session (2,112 once invoked), scanned A, original, Apache-2.0.

A product-analysis workflow that looks for both broken areas and overlooked opportunities using product data and the value delivered to each type of user.

In plain words
What is it for?
It helps investigate user and product issues, examine how features serve different user groups, identify causes behind weak or strong results, and prepare problems for idea workshops.
Why use it?
It helps teams avoid treating symptoms or feature requests as root problems and missing areas that are already working well.

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/vgrss/acumen/diagnose
Any agent
npx skills add VGrss/Acumen --skill diagnose
Clone the repo
git clone --depth 1 https://github.com/VGrss/Acumen

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 diagnose

README.md
[![agentmods](https://agentmods.dev/badge/skills/vgrss/acumen/diagnose.svg)](https://agentmods.dev/skills/vgrss/acumen/diagnose)
Your own site
<a href="https://agentmods.dev/skills/vgrss/acumen/diagnose"><img src="https://agentmods.dev/badge/skills/vgrss/acumen/diagnose.svg" alt="Measured on agentmods" height="20"></a>
Per session 47 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,112 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 $0.00047 $0.02112
Opus 5 $0.00023 $0.01056
Sonnet 5 $0.00009 $0.00422
Haiku 4.5 $0.00005 $0.00211

Measured 4d ago against content hash edbfba8cfb2e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

diagnose 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 4d 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.

.agents/skills/diagnose/SKILL.md · 167 lines

How it starts

The opening of the file, as written. The whole thing — 167 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MANDATORY PREPARATION

Invoke /product-thinking — it contains the Context Gathering Protocol and the AI Slop Test. Follow the protocol before proceeding.


Mindset

Symptoms are not problems. Requests are not needs. Bright spots are not luck. Your job is to find what is actually broken and what is quietly working and underexploited — both grounded in data and measured against the value you're supposed to deliver to each persona.

Most product problems are misdiagnosed at the framing stage. The team sees a symptom ("users don't use feature X"), jumps to a cause ("the UI is bad"), and builds a solution ("redesign the UI"). Meanwhile the real problem was that users never discovered feature X, or that it solves a problem they don't have.

And most opportunities are missed the same way — a metric is climbing, nobody asks why, and the chance to pour fuel on what's already working slips by. Teams fixate on what's broken and ignore what's working. Diagnose does both.

Your job is to slow down the jump from symptom to solution — and to surface where the product could win, not just where it's losing.

Context Pull

Before diagnosing anything, load the full picture:

  1. Product context. Read .acumen.md — strategy, positioning, north star, what success looks like.
  2. Feature inventory. Read .acumen/features.md — what we've built, feature health, known gaps and decay.
  3. Personas. Read .acumen/personas.md — who we serve, their jobs, their pain points, their workarounds.
  4. Value chain. Read .acumen/value-chain.md — the end-to-end workflow per persona. Use it to locate where a symptom occurs or where an opportunity sits, and whether it's a step we own, assist, or don't touch. If the value chain already lists opportunities against extension points, start there.
  5. Competitors. Read .acumen/competitors.md — competitive context, and where the white space is.

Data Pull

Data is the ground truth for both problems and opportunities. Check .acumen/sources.md and pull real numbers:

Read the full file on GitHub · 167 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. 4d ago First seen · 167 lines · 47 tokens per session scan A edbfba8cfb2e

Subscribe to this mod's changes

diagnose is a skill published in the GitHub repository VGrss/Acumen (11 stars, last pushed 29d ago), licensed Apache-2.0. It adds 47 tokens to every session and 2,112 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.

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