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 bvolpato/ivygrep --skill use-ivygrepgit clone --depth 1 https://github.com/bvolpato/ivygrepWrote 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/bvolpato/ivygrep/use-ivygrep)<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.
<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>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 | $0.00065 | $0.00418 |
| Opus 5 | $0.00032 | $0.00209 |
| Sonnet 5 | $0.00013 | $0.00084 |
| Haiku 4.5 | $0.00006 | $0.00042 |
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.
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 questionpath: absolute repository or worktree pathoutput:context_packbudget_tokens:8000since: 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.
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.
- 10d ago First seen · 46 lines · 65 tokens per session scan A c47c98087016
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.
Other skills, from other repositories
x-ray
Deep codebase exploration using semantic search and relationship mapping. Use when you need to understand the current codebase.
Sverklo Code Intelligence
Gives you deep codebase understanding — semantic search, blast-radius analysis, PR review, and health audits.
codemeridian-refactor
Plan safer refactors with CodeMeridian by checking graph freshness, exact symbols, impact, tests, duplication, and architecture risk before editing.
codemeridian-test-planning
Plan focused tests with CodeMeridian by finding relevant test shields, coverage gaps, impacted behavior, and the smallest useful test set before implementation.
human-cognitive-seed
Preserve and strengthen the user's independent reasoning during design, strategy, learning, interpretation, hypothesis work, and consequential decisions, and preserve justified durable context with explicit provenance when supported. Use when a task benefits from human-led judgment, model-building, productive…
codemeridian-context
Gather minimal, graph-grounded CodeMeridian context before implementation, refactoring, deletion, debugging, or test planning.