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.
git clone --depth 1 https://github.com/punt-labs/quarryWrote 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/commands/punt-labs/quarry/ingest-dev)<a href="https://agentmods.dev/commands/punt-labs/quarry/ingest-dev"><img src="https://agentmods.dev/badge/commands/punt-labs/quarry/ingest-dev/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/commands/punt-labs/quarry/ingest-dev"><img src="https://agentmods.dev/badge/commands/punt-labs/quarry/ingest-dev.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 | $0.00036 | $0.00426 |
| Opus 5.5 | $0.00014 | $0.00170 |
| Sonnet 5.5 | $0.00007 | $0.00085 |
| Haiku 4.5 | $0.00004 | $0.00043 |
Grade A, and why
ingest-dev 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- ingest — 88% identical, 6 lines differ
What it actually says
Input
Arguments: $ARGUMENTS
Determine the ingestion method:
- If it starts with
http://orhttps://: URL (auto-discovers sitemaps) - Otherwise it's a local path — a directory or a single file: Local path
(indexed via directory registration + sync; the
ingesttool itself only accepts URLs, so a local file is reached by registering the directory that contains it — this indexes the whole directory, not just the one file)
Expand ~ to the user's home directory, and resolve any relative path to an
absolute one against the current working directory, before calling any tool
(the tool sends the path as given, and a relative path resolved on the wrong
side registers the wrong directory).
Task
Call the appropriate tool(s):
- URL:
mcp__quarry-dev__ingestwithsourceset to the argument - Local path: Call
mcp__quarry-dev__register_directorywithdirectoryset to the absolute path. If the result containsFileNotFoundError(the daemon rejects both a nonexistent path and an existing file this way — there's no way to tell them apart from the error alone), retry once with the path's parent directory. Any other error (already registered, name conflict, etc.) is not a file-vs-directory problem — report it as-is, do not retry. Then callmcp__quarry-dev__sync_all_registrations
The result is already formatted by a PostToolUse hook and displayed above. Do not repeat or reformat the data. Do not send any text after the tool call.
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 · +23 tokens per session 9302d59369e9
- 1mo ago First seen · 39 lines · 13 tokens per session scan A e026d1f1085f
ingest-dev is a command published in the GitHub repository punt-labs/quarry (6 stars, last pushed 4d ago), licensed MIT. It adds 36 tokens to every session and 426 once invoked, about $0.0001 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 2026-08-31.
Other commands, from other repositories
setup-video-vision
Interactive setup wizard for claude-video-vision — configure backend, whisper, frames, and verify dependencies.
autosearch
Deep research via AutoSearch v2 tool-supplier — clarify → select channels → search → synthesize.
trace-claude-code
Control Opik tracing for your Claude Code sessions.
search-flights
Search award flight availability across airlines.
contracts-dev
Generate runtime contracts (preconditions, postconditions, invariants) from a Z specification.
partition-dev
Derive test cases from Z specification using TTF testing tactics.