Is the Claude Sleuth skill free?

Yes. The skill itself is free from elb-pr/sleuth. SkillProof publishes the install command and an independent test verdict at no cost.

What is the Claude Sleuth SkillProof Score?

8.0/10 — installs cleanly 4/5, triggers reliably 5/5, output vs. baseline 8/10, docs & honesty 3/5.

How do I install Claude Sleuth?

Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.

Can I use Claude Sleuth with Cursor, Copilot, Gemini CLI, Codex or other AI tools?

The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.

Claude Sleuth

56-task OSINT/due-diligence pipeline with real grading scripts, but core persistence needs external hosted MCP servers not mentioned in SKILL.md.

by elb-pr · elb-pr/sleuth

Works with setup

Install — copy the command Download source ↗

Test report

Verdict: Works with setup
Score: 8.0/10
Tested: Jul 14, 2026
Environment: Claude Code 2.x (agent harness)
Upstream re-checked: Aug 10, 2026 · c981bfd

Ran the bundled source_grader.py live on two real sources (an anonymous forum tip vs a UK Companies House filing) and got clean, reproducible Admiralty 6x6 grades with action recommendations — but the workflow's own constraints call CSDb/Thinking-Toolkit/Pigeon-Superstition-Superposition MCPs its 'only' collection instruments, and setting those up (2 Smithery-hosted servers plus self-hosting a Cloudflare Worker) is documented only in README.md, never in the SKILL.md the model actually reads at trigger time.

Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works

Installs cleanly 4/5
Triggers reliably 5/5
Output vs. baseline 8/10
Docs & honesty 3/5

What Claude Sleuth does

Drives a 6-phase, 56-task intelligence-cycle workflow (Admiralty 6x6 source grading, ACH hypothesis testing, ICD 203 briefings) for OSINT, due-diligence, and entity-network investigations, backed by 15 real Python scripts for grading, entity resolution, and evidence preservation. Triggers on beneficial-ownership tracing, sanctions screening, analytical briefings, or investigation-strategy requests, but its own constraints declare session-state and profiling MCPs as the 'only' collection instruments — those MCPs are hosted third-party or self-hosted infrastructure the SKILL.md never tells the user how to set up.

How to install Claude Sleuth

git clone https://github.com/elb-pr/sleuth
cd sleuth
mkdir -p ~/.claude/skills
cp -r skills/claude-sleuth ~/.claude/skills/sleuth

Skills live in ~/.claude/skills/ (global) or .claude/skills/ (per-project). Restart Claude Code after installing.

Commands — how to trigger Claude Sleuth

/sleuth 56-task OSINT/due-diligence pipeline with real grading scripts, but core persistence needs external hosted MCP servers not mentioned in SKILL.md.

It also activates on plain-language prompts like these:

Grade the reliability of this anonymous tip versus a filing
Run due diligence on this company's beneficial ownership
Screen this entity for sanctions exposure and score sources

Frequently asked questions

Is the Claude Sleuth skill free?: Yes. The skill itself is free from elb-pr/sleuth. SkillProof publishes the install command and an independent test verdict at no cost.
Does Claude Sleuth work with Claude Code?: We tested it with Claude Code 2.x (agent harness) on Jul 14, 2026. Verdict: Works with setup. Ran the bundled source_grader.py live on two real sources (an anonymous forum tip vs a UK Companies House filing) and got clean, reproducible Admiralty 6x6 grades with action recommendations — but the workflow's own constraints call CSDb/Thinking-Toolkit/Pigeon-Superstition-Superposition MCPs its 'only' collection instruments, and setting those up (2 Smithery-hosted servers plus self-hosting a Cloudflare Worker) is documented only in README.md, never in the SKILL.md the model actually reads at trigger time.
What is the Claude Sleuth SkillProof Score?: 8.0/10 — installs cleanly 4/5, triggers reliably 5/5, output vs. baseline 8/10, docs & honesty 3/5.
How do I install Claude Sleuth?: Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
Can I use Claude Sleuth with Cursor, Copilot, Gemini CLI, Codex or other AI tools?: The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.