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 laurigates/claude-plugins --skill ast-grep-searchgit clone --depth 1 https://github.com/laurigates/claude-pluginsWrote 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/laurigates/claude-plugins/ast-grep-search)<a href="https://agentmods.dev/skills/laurigates/claude-plugins/ast-grep-search"><img src="https://agentmods.dev/badge/skills/laurigates/claude-plugins/ast-grep-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.
<a href="https://agentmods.dev/skills/laurigates/claude-plugins/ast-grep-search"><img src="https://agentmods.dev/badge/skills/laurigates/claude-plugins/ast-grep-search.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 9 Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.Fix: Remove the model/provider override or disclose it prominently and require explicit operator approval before invoking an external coding CLI or billed model.
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 | $0.00040 | $0.02725 |
| Opus 5.5 | $0.00016 | $0.01090 |
| Sonnet 5.5 | $0.00008 | $0.00545 |
| Haiku 4.5 | $0.00004 | $0.00272 |
Grade A, and why
ast-grep-search scanned grade A with 1 finding 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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
ast-grep -p 'os.system($$$)' --lang py How it starts
The opening of the file, as written. The whole thing — 290 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ast-grep Structural Code Search & Refactoring
Structural code search and refactoring using ast-grep — matches code by its AST (abstract syntax tree) rather than text patterns.
When to Use This Skill
| Use this skill when... | Use something else instead when... |
|---|---|
| The pattern depends on AST structure (function shape, call form, argument count) | Searching plain text or regex matches → tools-plugin:rg-code-search |
| Refactoring API call sites across many files while preserving captured variables | Running a one-shot anti-pattern scan with a report → code-antipatterns |
| Hand-written structural search/replace for an ad-hoc migration | Functional refactors of a known file/directory → code-refactor |
| Building a new ast-grep rule for a codebase-specific smell | Looking up agentic flags for an existing linter → code-lint |
When to Use ast-grep vs Grep/ripgrep
| Use ast-grep when... | Use grep/rg when... |
|---|---|
| Pattern depends on code structure | Simple text or regex match |
| Need to match any number of arguments | Searching logs, docs, config |
| Refactoring across many files | One-off literal string search |
| Finding anti-patterns (empty catch, etc.) | Language doesn't matter |
| Replacing while preserving variables | Quick filename/line check |
Decision rule: If your search pattern contains wildcards for "any expression," "any arguments," or "any function name," use ast-grep.
Find References With the Sharpest Instrument
Promoted from ~/.claude/rules/tool-use-patterns.md. Edit refuses on a file
unread this session, so "read it first" is already a harness invariant. The
uncovered half is checking what else depends on what you're changing, and
the reflex there is grep, which cannot tell a call from a comment, a
definition from a mention, or foo() from "foo" in a string. Measured across
282 local sessions: ~2,400 code-symbol searches went through grep/rg,
against 6 ast-grep calls and 6 LSP calls.
What ships with it
1 file 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 Changed 922347cc7d71
- 1mo ago Changed · +31 lines 18958ca12278
- 1mo ago First seen · 259 lines · 40 tokens per session scan A 826a223947fb
ast-grep-search is a skill published in the GitHub repository laurigates/claude-plugins (59 stars, last pushed today), licensed MIT. It adds 40 tokens to every session and 2,725 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
review-feedback
Address code review/PR comments: verify each, then fix.
phpunit-test-team-reviewing
Use this skill when the user asks for a team-based, consensus, multi-reviewer, or red-team review of Shopware PHPUnit tests — trigger phrases like "team review these tests", "consensus review the tests in PR.
phpunit-test-reconciling
Internal sub-skill. Do not auto-activate. Use only when explicitly invoked by name by another skill or agent.
audit-comment-residue
Read-only classifier that flags residue in code comments: history narration, plan or session references, conversational asides, ticket or PR back-references, origin notes, and workarounds with no link or removal condition. Use when asked to 'audit code comments' or report which comments only make sense with the chat…
issue-analyzing
Use this skill when the user asks to analyze a specific GitHub issue, understand what area of code an issue affects, assess an issue's scope, or research the code context around an issue — example triggers like "analyze issue.
pr-analyzing
Use this skill when the user asks to analyze a specific GitHub pull request, review a PR's architectural impact, assess what changed in a PR and why it matters, or research the code relationships affected by a PR — example triggers like "analyze PR.