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.
git clone --depth 1 https://github.com/TheBeardedBearSAS/claude-craftWrote 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.
[](https://agentmods.dev/commands/thebeardedbearsas/claude-craft/search)<a href="https://agentmods.dev/commands/thebeardedbearsas/claude-craft/search"><img src="https://agentmods.dev/badge/commands/thebeardedbearsas/claude-craft/search.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00010 | $0.00836 |
| Opus 5 | $0.00005 | $0.00418 |
| Sonnet 5 | $0.00002 | $0.00167 |
| Haiku 4.5 | $0.00001 | $0.00084 |
Grade C, and why
search scanned grade C with 2 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 8d 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
- Rules: `grep -ri "<keyword>" .claude/rules/` Enumerates other installed skillsmediumAgent snooping
Other skills' SKILL.md files reveal prompts, capabilities and secrets that should be invisible to peers.
- Skill names: `find .claude/skills -name "*<keyword>*"` How it starts
The opening of the file, as written. The whole thing — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Search Claude Craft
Search commands, skills and agents by keyword across the entire Claude Craft framework.
Usage
/common:search <keyword>
Examples
/common:search testing
/common:search security
/common:search react
/common:search audit
Implementation
This command searches through:
- Commands in
.claude/commands/*/(name and content) - Skills in
.claude/skills/*/(name and description) - Agents in
.claude/agents/*/(name and description) - Rules in
.claude/rules/(title and content)
Results are ranked by relevance and display the top 5 matches.
Search Algorithm
- Search in command/skill/agent names (highest priority)
- Search in descriptions and frontmatter
- Search in file content (lower priority)
- Rank by keyword frequency and position
- Display top 5 results with context
Output Format
🔍 Search results for "testing":
Commands:
• /qa:tdd - TDD workflow (Red → Green → Refactor)
• /symfony:check-testing - Check Symfony testing compliance
• /react:check-testing - Check React testing compliance
Skills:
• testing - TDD/BDD testing patterns and best practices
• testing-symfony - Symfony-specific testing with PHPUnit/Pest
Agents:
• @tdd-coach - Guide through Test-Driven Development
Rules:
• 07-testing.md - Testing TDD/BDD — Quick Reference
Instructions for Claude
When a user invokes /common:search <keyword>:
-
Search across all commands, skills, agents, and rules
-
Use Grep tool with case-insensitive search (
-iflag) -
Search patterns:
- Command names:
find .claude/commands -name "*<keyword>*.md" - Skill names:
find .claude/skills -name "*<keyword>*" - Agent names:
grep -ri "<keyword>" .claude/agents/ - Rules:
grep -ri "<keyword>" .claude/rules/
- Command names:
-
Extract and format results:
- For commands: extract frontmatter
nameanddescription - For skills: extract directory name and SKILL.md frontmatter
- For agents: extract agent name from AGENT.md frontmatter
- For rules: extract title from markdown header
- For commands: extract frontmatter
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.
- 8d ago First seen · 114 lines · 10 tokens per session scan C 3bd44f1d0432
search is a command published in the GitHub repository TheBeardedBearSAS/claude-craft (105 stars, last pushed 5d ago), licensed MIT. It adds 10 tokens to every session and 836 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it C with 2 findings (reads agent configuration directories, enumerates other installed skills). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other commands, from other repositories
search
Search across all project artifacts by keyword, document type, or requirement ID.
search
Search across all project artifacts by keyword, document type, or requirement ID.
test-suite
Run comprehensive test suite with coverage analysis.
assemble-team
Assemble a pre-built agent team for parallel work - review, feature, debug, cross-platform, full-stack, or research.
standardize-claude-md
Add missing toolkit sections (Related Global Rules, Quick Start) to existing CLAUDE.md.
checklist
Generate a custom checklist for the current feature based on user requirements.