Agent skill

Solodit

by marchev in marchev/claudit

Search Solodit for similar smart contract security findings.

MITAuto-check passedSecurity

Install Solodit

skills CLI
$ npx skills add marchev/claudit --skill solodit -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install marchev/claudit solodit --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/marchev/claudit.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/solodit .claude/skills/solodit && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
solodit
GitHub stars
158
Token cost
~832 tokens
SKILL.md length
303 words
Files
1
Skills in repo
1
Repo updated
First seen
Licence
MIT

At a glance

Search Solodit for similar smart contract security findings.

  • Reviewing vulnerabilities
  • SKILL.md covers Available Tools, When to Use, Usage Patterns and Formatting Results — MANDATORY, plus 1 more section
  • Reaches solodit.cyfrin.io
  • Comparing to known issues

What it does

Solodit is an agent skill from marchev/claudit. Search Solodit for similar smart contract security findings. Use when reviewing vulnerabilities, comparing to known issues, or researching prior art from real audits.

Its SKILL.md is about 830 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Security, covering Smart contract auditing and Intellectual property. It works with Model Context Protocol. The repository describes itself as: MCP server for searching Solodit smart contract security findings. The licence is MIT.

When your agent uses it

  • Reviewing vulnerabilities
  • Comparing to known issues
  • Researching prior art from real audits

Example prompts

  • “/solodit”

What it can do on your machine

Read from SKILL.md and the folder at commit b9f0372. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Hosts in commands or code, which the agent is likely to contact:

    • solodit.cyfrin.io

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Solodit loads about 832 tokens when it runs. Until then it costs about 44 tokens; SKILL.md has 303 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~44
When it runs · the whole SKILL.md, loaded when a task matches
~832

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from marchev/claudit at commit b9f0372, republished under its MIT licence (© marchev). 303 words, ~832 tokens.

Download SKILL.mdSave it as .claude/skills/solodit/SKILL.md (or your agent's skills folder).
name
solodit
description
Search Solodit for similar smart contract security findings. Use when reviewing vulnerabilities, comparing to known issues, or researching prior art from real audits.

You have access to Solodit's database of 20k+ smart contract security findings via MCP tools. Use them to find prior art, research vulnerability patterns, and compare against known issues from real audits.

Available Tools

mcp__solodit__search_findings

Primary search. Supports keywords, severity, firms, tags, language, protocol, time period, sorting, and advanced filters.

mcp__solodit__get_finding

Get full details for a specific finding by Solodit URL or slug.

mcp__solodit__get_filter_options

Discover valid filter values (firms, tags, categories, languages). Call this first if unsure what values to use.

When to Use

  • Reviewing a vulnerability: Search for similar findings to check if it's a known pattern
  • Auditing a protocol: Search by protocol category, language, or tags relevant to the codebase
  • Researching a bug class: Search by tags (e.g., "Reentrancy", "Oracle") to find real examples
  • Checking prior art: Before reporting a finding, search for similar issues to reference
  • Studying an auditor: Use advanced_filters.user to find a specific researcher's findings

Usage Patterns

Find similar issues
search_findings(keywords="oracle price manipulation", severity=["HIGH", "MEDIUM"], sort_by="Quality")
Research by firm
search_findings(firms=["Sherlock"], severity=["HIGH"], reported="90")
Explore a vulnerability tag
search_findings(tags=["Reentrancy", "Flash Loan"], severity=["HIGH"], sort_by="Quality")
Protocol-specific research
search_findings(protocol="Uniswap", severity=["HIGH", "MEDIUM"])
search_findings(keywords="reentrancy", language="Solidity", sort_by="Quality")
High-quality solo findings (likely novel)
search_findings(
  tags=["Oracle"],
  advanced_filters={ quality_score: 4, max_finders: 1 }
)
Auditor research
search_findings(advanced_filters={ user: "0x52" }, severity=["HIGH"])

Formatting Results — MANDATORY

You MUST follow this format exactly. Do NOT use tables. Do NOT omit links.

Each finding in the MCP response includes a **Solodit:** line with a URL. You MUST include this URL for every finding.

Format each finding as:

1. **[HIGH] Title**
   Firm (Protocol) · Quality: X/5 · Finders: N
   → https://solodit.cyfrin.io/issues/...

2. **[MEDIUM] Title**
   Firm (Protocol) · Quality: X/5 · Finders: N
   → https://solodit.cyfrin.io/issues/...

NEVER use a table format. NEVER omit the Solodit URL. The URL line starting with → is required for every finding.

For detailed analysis, use get_finding to fetch full content for the most relevant results.

Tips

  • Start broad, then narrow with filters
  • Use sort_by="Quality" to surface the best-written findings first
  • Use sort_by="Rarity" to find unusual/novel vulnerability patterns
  • Combine tags with severity for targeted searches
  • If no results, try broader keywords or remove restrictive filters
  • Call get_filter_options if you're unsure about valid filter values

© marchev, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .claude/skills/solodit of marchev/claudit.

Open the folder on GitHubat commit b9f0372

Compare with similar skills

Solodit next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Solodit compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Solodit this skillmarchev/claudit158—~832Automated safety check: PassMIT
Patsnap Ip Searchingpatsnap/mcp112—~1.1kAutomated safety check: PassApache-2.0
Patsnap Triz Case Librarypatsnap/mcp112—~885Automated safety check: PassApache-2.0
Prior Art Searchillusionaireal/oh-my-patent100—~1.8kAutomated safety check: PassMIT
Patsnap Workspacepatsnap/mcp112—~777Automated safety check: PassApache-2.0
Patsnap Advanced Patent Searchpatsnap/mcp112—~650Automated safety check: PassApache-2.0

Similar skills

  • Patsnap Patent Research MCP for AI agents. An agent skill from patsnap/mcp.

    112 GitHub stars~1.1k tokensUpdated 1 mo ago
    Legal & ComplianceAuto-check passed
  • Patsnap TRIZ Case Library MCP for AI agents. An agent skill from patsnap/mcp.

    112 GitHub stars~885 tokensUpdated 1 mo ago
    Legal & ComplianceAuto-check passed
  • Prior Art Search

    illusionaireal/oh-my-patent

    A skill your agent uses when searching patents and technical literature for prior art, novelty, or patentability assessment.

    100 GitHub stars~1.8k tokensUpdated yesterday
    Legal & ComplianceAuto-check passed
  • Patsnap Workspace MCP for AI agents. An agent skill from patsnap/mcp.

    112 GitHub stars~777 tokensUpdated 1 mo ago
    Legal & ComplianceAuto-check passed
  • Patsnap Advanced Patent Search MCP for AI agents. An agent skill from patsnap/mcp.

    112 GitHub stars~650 tokensUpdated 1 mo ago
    Legal & ComplianceAuto-check passed
  • Biological sequence and modality intelligence via Patsnap MCP.

    112 GitHub stars~771 tokensUpdated 1 mo ago
    Legal & ComplianceAuto-check passed

Questions about Solodit

What does Solodit do?

Search Solodit for similar smart contract security findings. Solodit is an agent skill from marchev/claudit. Search Solodit for similar smart contract security findings.

When should I use Solodit?

Solodit fits situations like: reviewing vulnerabilities; comparing to known issues; researching prior art from real audits.

How do I install Solodit in Claude Code?

Run `npx skills add marchev/claudit --skill solodit -a claude-code`. Or copy the skill folder (.claude/skills/solodit in marchev/claudit) into .claude/skills/solodit in your project. Claude Code loads it when a task matches its description.

How do I install Solodit in Codex?

Run `npx skills add marchev/claudit --skill solodit -a codex`. Or copy the skill folder (.claude/skills/solodit in marchev/claudit) into .agents/skills/solodit in your project. Codex loads it when a task matches its description.

Can I use Solodit in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add marchev/claudit --skill solodit -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/solodit, .gemini/skills/solodit, .github/skills/solodit and .opencode/skills/solodit in your project.

What does Solodit need to run?

SKILL.md names no scripts, command-line tools or credentials: Solodit is instructions for the agent only.

Does Solodit access the network?

SKILL.md names 1 domain. In commands or code: solodit.cyfrin.io; the agent is likely to contact it when it follows the instructions. This is read from the text; nothing was executed.

Is Solodit safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Solodit use?

Solodit is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Solodit use?

About 832 tokens (SKILL.md is roughly 3.3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Solodit?

Skills that share tags, products or a category with Solodit: Patsnap Ip Searching (patsnap/mcp, 112 stars), Patsnap Triz Case Library (patsnap/mcp, 112 stars), Prior Art Search (illusionaireal/oh-my-patent, 100 stars) and Patsnap Workspace (patsnap/mcp, 112 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Solodit?

marchev (a GitHub user) maintains it in marchev/claudit, which has 158 GitHub stars. The repository was last updated on April 23, 2026.

Source: marchev/claudit on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.