deep

A structured analysis workflow for difficult ad-hoc tasks. It examines the request, hidden assumptions, existing solutions, alternatives, edge cases, and points where work should stop for confirmation.

In plain words
What is it for?
It is for planning non-trivial code changes before implementation, when the user wants written analysis first.
Why use it?
It reduces the chance of changing code based on a shallow or incorrect understanding of the task.

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/alphabravo-oss/guild/deep
Any agent
npx skills add alphabravo-oss/guild --skill deep
Clone the repo
git clone --depth 1 https://github.com/alphabravo-oss/guild

Made for: Claude Code, Codex.

Per session 84 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,034 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 $0.00084 $0.01034
Opus 5 $0.00042 $0.00517
Sonnet 5 $0.00017 $0.00207
Haiku 4.5 $0.00008 $0.00103

Measured 2d ago against content hash 3285ef185a0c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

deep 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.

plugins/adhoc/skills/deep/SKILL.md · 88 lines

How it starts

The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/adhoc:deep — Deep Methodical Pass

You have been invoked because the user wants a deeper, more deliberate analysis than the always-on adhoc preamble provides. Do not write or edit code in this skill. Produce a written analysis. The user will decide what to do with it.

Mindset

You are not racing. You are not pattern-matching. You are reasoning from the actual code and the actual request. If you find yourself wanting to stop early, that is the signal to keep going — the gap between "plausible" and "correct" is exactly where ad-hoc work goes wrong.

Your default assumption is that you have misunderstood something. Your job in this skill is to find what.

The 7 steps

Walk every step. Do not collapse them. If a step turns up nothing, say so explicitly — silent skips are how shallow analysis disguises itself as thorough.

1. RESTATE — Frame the task

  • In one paragraph, restate what the user is asking, in your own words.
  • Explicitly distinguish: what they said, what they likely meant, and what they might also mean (alternative interpretations).
  • If the alternative interpretations would lead to materially different work, STOP and ask the user which they want before continuing.

2. ASSUMPTIONS — Hunt the hidden ones

  • List every assumption you would otherwise make silently. Aim for at least 5 — fewer means you are not looking hard enough.
  • For each, mark VERIFIED (you read the code / checked) or UNVERIFIED (inferring).
  • For each UNVERIFIED, decide: verify now (Read/Grep/Glob), ask the user, or accept-with-flag. Default: verify.

3. PRIOR ART — What already exists

  • Search the codebase for existing solutions to this problem or adjacent ones (Grep / Glob).
  • Search CLAUDE.md, AGENTS.md, persisted memory, and recent git history for related decisions, prior incidents, or rejected approaches.
  • If a similar pattern exists, mirror it instead of inventing a new one. If you intend to deviate, justify the deviation explicitly.

4. ALTERNATIVES — At least three approaches

Read the full file on GitHub · 88 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. 2d ago First seen · 88 lines · 84 tokens per session scan A 3285ef185a0c

Subscribe to this mod's changes

deep is a skill published in the GitHub repository alphabravo-oss/guild (2 stars, last pushed 3d ago), licensed MIT. It adds 84 tokens to every session and 1,034 once invoked, about $0.0004 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