use-ivygrep

use-ivygrep is a skill for Claude Code, Codex from bvolpato/ivygrep. It costs 65 tokens per session (418 once invoked), scanned A, original, MIT.

A set of instructions for using ivygrep to gather focused local project context before changing, debugging, reviewing, or explaining code.

In plain words
What is it for?
It guides focused searches for callers, dependents, tests, configuration, documentation, stack traces, and changes since a base branch.
Why use it?
It helps an agent find the right files and relationships in an unfamiliar repository without scanning everything broadly.

Skill for Claude CodeCodex

Written for Claude Code and Codex: shipped in a Claude Code plugin, but also agents/openai.yaml present.

Part of the ivygrep plugin — 1 skill, 1 MCP server shipped together

Good fit It guides focused searches for callers, dependents, tests, configuration, documentation, stack traces, and changes since a base branch.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/bvolpato/ivygrep/use-ivygrep
Install

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.

Any agent
npx skills add bvolpato/ivygrep --skill use-ivygrep
Clone the repo
git clone --depth 1 https://github.com/bvolpato/ivygrep

Made for: Claude Code, Codex.

Or install ivygrep, the plugin that ships this one along with the rest of its 1 skill, 1 MCP server.

Wrote 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.

agentmods badge for use-ivygrep

README.md
[![agentmods](https://agentmods.dev/badge/skills/bvolpato/ivygrep/use-ivygrep/github.svg)](https://agentmods.dev/skills/bvolpato/ivygrep/use-ivygrep)
Your own site
<a href="https://agentmods.dev/skills/bvolpato/ivygrep/use-ivygrep"><img src="https://agentmods.dev/badge/skills/bvolpato/ivygrep/use-ivygrep/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.

agentmods 80×15 button for use-ivygrep

Your own site · 80×15
<a href="https://agentmods.dev/skills/bvolpato/ivygrep/use-ivygrep"><img src="https://agentmods.dev/badge/skills/bvolpato/ivygrep/use-ivygrep.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 65 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 418 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00065 $0.00418
Opus 5 $0.00032 $0.00209
Sonnet 5 $0.00013 $0.00084
Haiku 4.5 $0.00006 $0.00042

Measured 10d ago against content hash c47c98087016, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

use-ivygrep 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 10d 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.

plugins/ivygrep/skills/use-ivygrep/SKILL.md · 46 lines

What it actually says

Use ivygrep

Start with one context request. Pass absolute active repository or worktree path.

When MCP tool ig_search is available, call it with:

  • query: concrete task, failure, or question
  • path: absolute repository or worktree path
  • output: context_pack
  • budget_tokens: 8000
  • since: base branch when current changes matter

CLI fallback:

ig context "<task>" --since main --budget 8000 /absolute/repository/path

On a large repository the first call may return status: indexing with progress instead of results. That is not an error: the index keeps building in the background. Wait retry_after_secs, then repeat the same call. Do not retry immediately or fall back to broad filesystem scans.

Use returned selection reasons and relationships to choose files. Verify relevant snippets against source before editing. Treat missing expected code as retrieval evidence, not proof that code does not exist.

Use one focused search only when context pack leaves a concrete gap:

ig --literal "<identifier>" -n 10 /absolute/repository/path

MCP ig_search with output: hits returns at most limit files (default 10) and hits_per_file hits per file (default 3). Check truncated, total_matches, and more_hits_in_file; narrow query or path, or raise limit, instead of repeating broad queries.

Do not repeat broad synonymous queries. Continue with normal code inspection, implementation, and project validation after ivygrep identifies working set.

Files

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.

Changes

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.

  1. 10d ago First seen · 46 lines · 65 tokens per session scan A c47c98087016

Subscribe to this mod's changes

use-ivygrep is a skill published in the GitHub repository bvolpato/ivygrep (6 stars, last pushed 4d ago), licensed MIT. It adds 65 tokens to every session and 418 once invoked, about $0.0003 per session on Opus 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 2026-08-31.