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 agentmods add skills/yetidevworks/ygrep/claude-codenpx skills add yetidevworks/ygrep --skill claude-codegit clone --depth 1 https://github.com/yetidevworks/ygrepWhat 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 | $0.00055 | $0.00947 |
| Opus 5 | $0.00028 | $0.00474 |
| Sonnet 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 3d 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.
- 3d ago First seen · 72 lines · 55 tokens per session scan A 1ce72f7dadb8
ygrep is a skill published in the GitHub repository yetidevworks/ygrep (58 stars, last pushed 6d ago), licensed MIT. It adds 55 tokens to every session and 947 once invoked, about $0.0003 per session on Opus 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
weekly-summary
Generate a comprehensive summary of AI coding sessions from the past week. Use when the user says "weekly summary", "what did I do this week", "summarize my week", "weekly recap", "week in review", or asks for a summary of recent work across projects.
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)…
handoff
Wrap up a work session so the next session (or another agent) can pick up cleanly — what was done, what's in flight, what to watch out for. Use when ending a session, switching tasks, or asked to hand off, wrap up, or save state for later.
memtrace-daily
Orient at the start of a coding session, review what recently changed in a repository, and self-audit after completing work. Use when the user wants the daily briefing (what changed in the last 24h with complexity deltas), hotspots (complexity × churn refactor priorities), or a session review (clean/review/risky…
siyuan-cli
操作思源笔记的 CLI 工具。当用户要求管理笔记本、文档、块、标签、搜索笔记、导入导出、管理资源、同步数据时使用此 skill。可执行路径下的 siyuan-cli.exe(或 go run .)。不包含 auth/chat/mcp 命令。.
frg-search
Fast indexed code search using frg (5x faster than ripgrep).