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 bahayonghang/my-ai-cli-toolkit --skill ripgrepgit clone --depth 1 https://github.com/bahayonghang/my-ai-cli-toolkitWrote 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/bahayonghang/my-ai-cli-toolkit/ripgrep)<a href="https://agentmods.dev/skills/bahayonghang/my-ai-cli-toolkit/ripgrep"><img src="https://agentmods.dev/badge/skills/bahayonghang/my-ai-cli-toolkit/ripgrep/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/bahayonghang/my-ai-cli-toolkit/ripgrep"><img src="https://agentmods.dev/badge/skills/bahayonghang/my-ai-cli-toolkit/ripgrep.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 | $0.00081 | $0.02326 |
| Opus 5.5 | $0.00032 | $0.00930 |
| Sonnet 5.5 | $0.00016 | $0.00465 |
| Haiku 4.5 | $0.00008 | $0.00233 |
Grade A, and why
ripgrep 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.
How it starts
The opening of the file, as written. The whole thing — 193 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ripgrep Text Search
Use ripgrep (rg) when the user needs fast text or regex content search from the command line. The useful outcome is a copy-pasteable command plus a clear statement of what it matches, what it skips, and why.
Triage
Start with the smallest tool that can answer the question.
- For trivial in-conversation lookups, use the harness's built-in ripgrep-backed search tool instead of shelling out to rg.
- Use rg for exact names, strings, regex content searches, file lists, counts, and pipeline-friendly output.
- Use ast-grep for syntax shape: descendants, ancestors, call forms, decorators, missing constructs, or nested contexts.
- Use language tooling for semantic facts such as type resolution, references, imports, or rename safety.
Before trusting local behavior, verify the binary: rg --version should print
a ripgrep version plus enabled features such as +PCRE2. If it does not, run
which rg — an alias or another tool named rg may shadow it.
Defaults Model
rg is a filter wrapped around a search. By default it:
- searches the current directory recursively (
rg fooequalsrg foo ./), - respects
.gitignore,.ignore, and.rgignorerules (precedence:.rgignoreover.ignoreover.gitignore), - skips hidden files and directories,
- skips binary files (any file containing a NUL byte),
- does not follow symlinks (opt in with
-L/--follow).
Escalation ladder: -u disables ignore-file handling, -uu also searches
hidden files, -uuu also searches binary files — roughly grep -r with no
smart filtering. Individual toggles: --no-ignore, --hidden, -a/--text.
When rg "can't find" a file, diagnose before changing the pattern:
rg --files | rg name— is the file in the searched set at all?rg pattern --debug— which ignore rule or config excluded it? A*rule in the global gitignore is the most common cause.rg pattern -uuu— does the match appear with all filtering off?
Workflow
- Compose the simplest command that could work; prefer
-Ffor literals. - Dry-run the file set with
--filesplus your-g/-tfilters when the search scope matters. - Run on a narrow path first (
rg pattern src/module), then widen. - For complex or shell-hostile patterns, write one pattern per line to a
file and use
-f patterns.txt(patterns are ORed). On Windows this is the preferred escape hatch from quoting problems; save the file as UTF-8 without BOM. - Report the command, what it matches, and what it may miss.
What ships with it
4 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 · 193 lines · 81 tokens per session scan A c905f2d708ac
ripgrep is a skill published in the GitHub repository bahayonghang/my-ai-cli-toolkit (17 stars, last pushed 6d ago), licensed MIT. It adds 81 tokens to every session and 2,326 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-08-30.
Other skills, from other repositories
ygrep
IMPORTANT: Try ygrep FIRST for all code and file searches before using Grep, Glob, or Task explore. ygrep uses a pre-built full-text index and returns results in milliseconds. Fall back to built-in tools only if ygrep returns no results.
code-search
This skill should be used when the user asks to "search code", "find in files", "grep for", "look for pattern", "search the codebase", "find references to", "find usages of", "search for function", "find where X is defined", or needs to search file contents across a directory tree. Provides guidance on using the…
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…
x-ray
Deep codebase exploration using semantic search and relationship mapping. Use when you need to understand the current codebase.
tilth
Use the tilth CLI for code reading, outlining, search, callers, blast-radius deps, and structural diffs. Activate when the user asks to explore a repo, find a symbol, trace callers, read a file, view a diff, or analyze impact. Prefer tilth over grep/cat/find/ls — one invocation returns AST-aware outlines, definitions…
codebase-search
Task-specific semantic code and documentation retrieval. Use compact context for unfamiliar repository orientation, direct lookup for known definitions, graph tools for relationships, and grep for exhaustive literal matches.