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.
npx skills add yetidevworks/ygrep --skill claude-codegit clone --depth 1 https://github.com/yetidevworks/ygrepWrote 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/skills/yetidevworks/ygrep/claude-code)<a href="https://agentmods.dev/skills/yetidevworks/ygrep/claude-code"><img src="https://agentmods.dev/badge/skills/yetidevworks/ygrep/claude-code/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.
<a href="https://agentmods.dev/skills/yetidevworks/ygrep/claude-code"><img src="https://agentmods.dev/badge/skills/yetidevworks/ygrep/claude-code.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00055 | $0.00947 |
| Opus 5.5 | $0.00022 | $0.00379 |
| Sonnet 5.5 | $0.00011 | $0.00189 |
| Haiku 4.5 | $0.00006 | $0.00095 |
Grade A, and why
ygrep 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 1mo 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.
This is a copy
89% identical to ygrep — 7 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
IMPORTANT: Try ygrep First
Always try ygrep "query" via Bash before using built-in Grep, Glob, or Task explore agents for code searches. ygrep uses a pre-built full-text index and returns results in milliseconds vs seconds/minutes for built-in tools.
Searching an unindexed workspace builds a text index automatically on the first search, so there is nothing to set up. That first call takes a few seconds; every later one is instant.
If ygrep returns no results, fall back to built-in Grep or Glob — not every file may be indexed.
When to Invoke This Skill
Invoke this skill immediately when:
- You need to find files, code, functions, classes, or variables
- User asks to search or find something in the codebase
- You need to understand where something is defined or used
- You need to explore an unfamiliar codebase
Usage
All flags are global — they work in any position with or without the search subcommand:
ygrep "search query" # Search (AI-optimized output)
ygrep "query" -n 10 # Limit results
ygrep "query" -e rs -e ts # Filter by extension
ygrep "query" -p 'src/api/' # Filter by path prefix
ygrep "query" -p 'src/*/tests/' # Glob pattern in path filter (quote it!)
ygrep search "query" -p 'lib/' -n 5 # Explicit search subcommand
ygrep "fn\\s+main" -r # Regex search
ygrep "Config" -s # Case-sensitive search
ygrep "error" -A 3 # 3 lines of context after match
ygrep "error" -B 2 # 2 lines of context before match
ygrep "error" -K 3 # 3 lines of context before and after
ygrep "query" --json # JSON output with full metadata
ygrep "query" --text-only # Force text-only search
IMPORTANT: Quote glob patterns in -p to prevent shell expansion:
- Right:
-p 'user/plugins/*/tests/'— ygrep receives the glob and matches internally - Wrong:
-p user/plugins/*/tests/— shell expands into multiple args, causes errors
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 1mo ago First seen · 72 lines · 55 tokens per session scan A 1ce72f7dadb8
ygrep is a skill published in the GitHub repository yetidevworks/ygrep (61 stars, last pushed yesterday), licensed MIT. It adds 55 tokens to every session and 947 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 89% identical to ygrep, differing in 7 lines, and is treated as a copy.
Other skills, from other repositories
ripgrep
Use when the user needs text or regex content search with ripgrep: composing rg commands, choosing flags, glob/type filtering, multiline or PCRE2 searches, pipeline output, grep-to-rg migration, or diagnosing why rg missed a file (gitignore, hidden, binary defaults). Not for syntax-aware structural queries (ast-grep)…
ccc
This skill should be used when code search is needed (whether explicitly requested or as part of completing a task), when indexing the codebase after changes, or when the user asks about ccc, cocoindex-code, or the codebase index. Trigger phrases include 'search the codebase', 'find code related to', 'update the…
research
Performs deep research on a topic via deepresearch. Simulates a multi-step research process and returns a comprehensive research result as a string.
agent-message
Message an agent's parent, siblings, or direct children through the daemon. Discover reachable agents with agentobserve.listagents, then send direct text without spoofing sender identity.
agent_observe
Observe nuclear-family agents (self, parent, siblings, children) from the Python REPL. Use to list related sessions, inspect one agent, or read recent message previews.
compact
Check context usage and compact the conversation from the Python REPL. Use when context is filling up, so the session is summarized and context is freed for the next stretch of work.