deep-analysis

deep-analysis is a skill for Claude Code from davila7/claude-with-skills. It costs 35 tokens per session (723 once invoked), scanned A, original, MIT.

A detailed method for investigating difficult software architecture or security problems. It calls for reviewing the relevant code, history, tests, configuration, and documentation before reaching a conclusion.

In plain words
What is it for?
Use it for architecture decisions, security reviews, difficult bugs, or investigations where a quick code inspection has not found the root cause.
Why use it?
It helps avoid stopping at a visible symptom when the real cause is elsewhere in the codebase. The broader review provides evidence for complex technical decisions or security findings.

Skill for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter. Also seen: model in frontmatter.

Good fit Use it for architecture decisions, security reviews, difficult bugs, or investigations where a quick code inspection has not found the root cause.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/davila7/claude-with-skills/deep-analysis
About the project

Claude With Skills is a progressive course that teaches developers to create reusable, portable Agent Skills for Claude Code, from basic SKILL.md files to advanced automation and plugin packaging. It is intended for developers who want repeatable instructions and workflows instead of repeatedly pasting the same guidance. The catalogue contains the course's skills, agents, and instruction.

davila7/claude-with-skills · 11 stars · on GitHub · claude-with-skills.vercel.app

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.

Any agent
npx skills add davila7/claude-with-skills --skill deep-analysis
Clone the repo
git clone --depth 1 https://github.com/davila7/claude-with-skills

Made for: Claude Code.

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 deep-analysis

README.md
[![agentmods](https://agentmods.dev/badge/skills/davila7/claude-with-skills/deep-analysis/github.svg)](https://agentmods.dev/skills/davila7/claude-with-skills/deep-analysis)
Your own site
<a href="https://agentmods.dev/skills/davila7/claude-with-skills/deep-analysis"><img src="https://agentmods.dev/badge/skills/davila7/claude-with-skills/deep-analysis/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 deep-analysis

Your own site · 80×15
<a href="https://agentmods.dev/skills/davila7/claude-with-skills/deep-analysis"><img src="https://agentmods.dev/badge/skills/davila7/claude-with-skills/deep-analysis.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 35 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 723 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 $0.00035 $0.00723
Opus 5 $0.00017 $0.00362
Sonnet 5 $0.00007 $0.00145
Haiku 4.5 $0.00003 $0.00072

Measured 10d ago against content hash 78a1653dfb82, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

deep-analysis 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 10d 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.

src/content/docs/02-intermediate/lesson-07-model-and-effort/examples/deep-analysis/SKILL.md · 71 lines

How it starts

The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Deep analysis

ultrathink

Perform a thorough analysis of the described problem or codebase area. Do not skip steps under time or context pressure. This skill intentionally uses extended reasoning — use it.

Step 1: Gather all relevant context

Before forming any hypothesis, collect the raw material:

  • Read all files directly involved in the problem area
  • Check git history for the relevant files: git log --oneline --follow -20 <file> for each key file, then git show <hash> for commits that look relevant
  • Look for tests that cover the area: they describe the intended behavior
  • Look for related configuration (environment variables, feature flags, build configuration)
  • Check for any documentation: comments, ADRs, or README sections that mention the area

Do not stop gathering context when you think you understand the issue. The full picture often requires reading more than the most obvious files.

Step 2: Identify the core issue or question

State, in one or two sentences, what the fundamental question or problem is. Separate it from symptoms. For example:

  • Symptom: "The API returns 500 errors intermittently"
  • Core question: "Is this a race condition in the connection pool, an unhandled exception in a specific code path, or an infrastructure issue?"

If you are doing an architectural analysis, state the specific decision or tradeoff being evaluated.

Step 3: Consider multiple hypotheses or approaches

Do not converge on the first plausible explanation. List at least three distinct hypotheses or approaches:

  • For bug analysis: three distinct root causes that could explain the observed behavior
  • For architecture decisions: three distinct design approaches with different tradeoff profiles
  • For security reviews: three distinct vulnerability classes to investigate

For each, note what evidence would confirm or rule it out.

Step 4: Evaluate tradeoffs

For each hypothesis or approach, evaluate:

Evidence for: What in the codebase supports this explanation or approach? Evidence against: What contradicts it or makes it unlikely? Risk: If this hypothesis is wrong or this approach is chosen, what goes wrong? Cost to verify or implement: How much effort would confirming or executing this require?

Read the full file on GitHub · 71 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. 10d ago First seen · 71 lines · 35 tokens per session scan A 78a1653dfb82

Subscribe to this mod's changes

deep-analysis is a skill published in the GitHub repository davila7/claude-with-skills (11 stars, last pushed 3mo ago), licensed MIT. It adds 35 tokens to every session and 723 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.