raven-search

raven-search is a command for Claude Code from giggsoinc/raven. It costs 42 tokens per session (302 once invoked), scanned A, original, MIT.

A command for finding and reviewing Claude skills, which are reusable instructions that extend a coding assistant. It searches selected sources, checks each skill for security issues, shows a preview, and asks for approval before installation.

In plain words
What is it for?
Use it to search for a skill, audit a selected skill, install it after approval, or list approved skills.
Why use it?
It reduces the risk of installing unsafe or unsuitable assistant instructions. It also keeps approved skills listed for later reference.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: reads .claude/ paths; mentions Claude Code.

Part of the raven plugin — 63 skills, 13 commands, 10 agents, 5 hooks, 1 MCP server shipped together

Good fit Use it to search for a skill, audit a selected skill, install it after approval, or list approved skills.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/giggsoinc/raven/raven-search
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.

Clone the repo
git clone --depth 1 https://github.com/giggsoinc/raven

Made for: Claude Code.

Or install raven, the plugin that ships this one along with the rest of its 63 skills, 13 commands, 10 agents, 5 hooks, 1 MCP server.

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 raven-search

README.md
[![agentmods](https://agentmods.dev/badge/commands/giggsoinc/raven/raven-search/github.svg)](https://agentmods.dev/commands/giggsoinc/raven/raven-search)
Your own site
<a href="https://agentmods.dev/commands/giggsoinc/raven/raven-search"><img src="https://agentmods.dev/badge/commands/giggsoinc/raven/raven-search/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 raven-search

Your own site · 80×15
<a href="https://agentmods.dev/commands/giggsoinc/raven/raven-search"><img src="https://agentmods.dev/badge/commands/giggsoinc/raven/raven-search.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 42 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 302 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 $0.00042 $0.00302
Opus 5 $0.00021 $0.00151
Sonnet 5 $0.00008 $0.00060
Haiku 4.5 $0.00004 $0.00030

Measured 9d ago against content hash afd02744a72e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

raven-search 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 9d 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.

commands/raven-search.md · 44 lines

What it actually says

Search for skills, audit them, and install with approval.

Usage

/raven-search {query}           ← search
/raven-search --install {name}  ← install with audit + approval
/raven-search --list            ← show approved skills

Steps

Search

Run: python3 .claude/scripts/skill-search.py --query "{query}" Show results table. Prompt: "Which would you like to install? (number or full_name)"

Install + Audit

Run: python3 .claude/scripts/skill-search.py --install "{full_name}"

Script will:

  1. Fetch SKILL.md from source
  2. Run automated security audit
  3. Show first 15 lines for manual review
  4. Block if critical issues found
  5. Ask for approval (yes/no)
  6. Install to .claude/skills/ if approved
  7. Add to manifest.approved_skills
  8. Remind to restart Claude Code

After install

Remind developer:

  • Review full SKILL.md before using
  • Pin to commit hash for production use
  • Re-audit on every update
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. 9d ago First seen · 44 lines · 42 tokens per session scan A afd02744a72e

Subscribe to this mod's changes

raven-search is a command published in the GitHub repository giggsoinc/raven (5 stars, last pushed 9d ago), licensed MIT. It adds 42 tokens to every session and 302 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 2026-08-31.