Is the Ghost Repo Context skill free?

Yes. The skill itself is free from ghostsecurity/skills. SkillProof publishes the install command and an independent test verdict at no cost.

What is the Ghost Repo Context SkillProof Score?

9.2/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 8/10, docs & honesty 5/5.

How do I install Ghost Repo Context?

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 Ghost Repo Context 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.

Ghost Repo Context

Maps a repo into a structured repo.md with per-project criticality and sensitive-data tags

by ghostsecurity · ghostsecurity/skills

Tested · Works

Install — copy the command Download source ↗

Test report

Verdict: Tested · Works
Score: 9.2/10
Tested: Jul 21, 2026
Environment: Claude Code 2.x (agent harness)

⚠ This skill is no longer available upstream. Our re-check on Aug 10, 2026 couldn't find it any more (SKILL.md not found in repo tree). The test below is what we measured on Jul 21, 2026 and we're leaving it up as a record — but there is nothing left to install, so we've removed the command.

Fetched SKILL.md and its 3 referenced files (detector.md, summarizer.md, template-repo.md), all HTTP 200; frontmatter parses with name+description and no security smells (explicitly bans WebFetch/WebSearch, no curl|sh or base64). Built a sample multi-stack repo (Flask api/ + React web/ + GitHub Actions) and produced two artifacts: a baseline overview (one flat "monorepo" description, 20 lines) and a skill-following repo.md (99 lines) that split the repo into three separate projects with per-directory 0.0-1.0 criticality scores, typed sensitive-data tags (PII/login/payment), and business-criticality ratings. The skill output is concretely richer and matches its stated security-context purpose. Wrote output to scratchpad rather than the real $HOME/.ghost per house rules.

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

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

What Ghost Repo Context does

Scans a repository's directory structure, detects distinct technology stacks as separate projects (backend, frontend, iac, cli, library), and writes a structured repo.md with per-directory criticality scores, sensitive-data-type tags, and business-criticality ratings. Triggers when the user wants a codebase overview, project-structure map, or repository context to feed a downstream security analysis. Local-only: it explicitly forbids WebFetch/WebSearch and works purely from files in the repo.

How to install Ghost Repo Context

Nothing to install: the source repository no longer has this skill. If the author brings it back, our daily re-check will pick it up and the command will reappear here.

Commands — how to trigger Ghost Repo Context

/ghost-repo-context Maps a repo into a structured repo.md with per-project criticality and sensitive-data tags

It also activates on plain-language prompts like these:

Map out this repo's structure before I dig in
Document our project's dependencies in repo.md
Give me a codebase overview before a security review

Frequently asked questions

Is the Ghost Repo Context skill free?: Yes. The skill itself is free from ghostsecurity/skills. SkillProof publishes the install command and an independent test verdict at no cost.
Does Ghost Repo Context work with Claude Code?: We tested it with Claude Code 2.x (agent harness) on Jul 21, 2026. Verdict: Tested · Works. Fetched SKILL.md and its 3 referenced files (detector.md, summarizer.md, template-repo.md), all HTTP 200; frontmatter parses with name+description and no security smells (explicitly bans WebFetch/WebSearch, no curl|sh or base64). Built a sample multi-stack repo (Flask api/ + React web/ + GitHub Actions) and produced two artifacts: a baseline overview (one flat "monorepo" description, 20 lines) and a skill-following repo.md (99 lines) that split the repo into three separate projects with per-directory 0.0-1.0 criticality scores, typed sensitive-data tags (PII/login/payment), and business-criticality ratings. The skill output is concretely richer and matches its stated security-context purpose. Wrote output to scratchpad rather than the real $HOME/.ghost per house rules.
What is the Ghost Repo Context SkillProof Score?: 9.2/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 8/10, docs & honesty 5/5.
How do I install Ghost Repo Context?: 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 Ghost Repo Context 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.