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/quarry-dev)<a href="https://agentmods.dev/commands/punt-labs/quarry/quarry-dev"><img src="https://agentmods.dev/badge/commands/punt-labs/quarry/quarry-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/quarry-dev"><img src="https://agentmods.dev/badge/commands/punt-labs/quarry/quarry-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 | $0.00005 | $0.00539 |
| Opus 5.5 | $0.00002 | $0.00216 |
| Sonnet 5.5 | $0.00001 | $0.00108 |
| Haiku 4.5 | $0.00001 | $0.00054 |
Grade A, and why
quarry-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 28d 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
Input
Arguments: $ARGUMENTS
Parse the first token as a subcommand. Default to status if empty.
Subcommands
- status (default): Call
mcp__quarry-dev__status - sync: Run
quarry syncvia the Bash tool withrun_in_background: true. This avoids blocking the conversation during long syncs. You will be notified when it completes. If a non-default database was selected viause, pass--db <name>to the CLI command. - collections: Call
mcp__quarry-dev__listwithkindset to"collections" - databases: Call
mcp__quarry-dev__listwithkindset to"databases" - registrations: Call
mcp__quarry-dev__listwithkindset to"registrations" - use
<name>: Callmcp__quarry-dev__usewithnameset to the second token. If no name is given afteruse, reply with brief usage:/quarry-dev use <database-name> - enable: Run
quarry enablevia the Bash tool. If a directory argument follows, pass it as a positional argument. Supports--collection <name>to override the collection name. - disable: Run
quarry disablevia the Bash tool. If a directory argument follows, pass it as a positional argument. Supports--keep-datato preserve indexed data in LanceDB. - missions sync: Call
mcp__quarry-dev__missions_sync. Files each frozen ethos mission round of this repo into the worker's memory; run it afterethos mission close. Passmissionwhen a mission id follows,dry_run: truefor--dry-run, andforce: truefor--force.
Output
For sync: after launching the background command, briefly confirm it's running (e.g., "Syncing in background — you'll be notified when done."). Do not block or poll.
For all other subcommands: emit the tool output exactly as returned — character for character, including the leading ▶ unicode character. Do not reformat, add commentary, wrap in code fences, convert to markdown tables, or add boxes around the output.
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.
- 28d ago Changed · +1 lines 95d2703a1a0c
- 1mo ago Changed 313438b6eca5
- 1mo ago First seen · 29 lines · 5 tokens per session scan A 65605df05416
quarry-dev is a command published in the GitHub repository punt-labs/quarry (6 stars, last pushed 2d ago), licensed MIT. It adds 5 tokens to every session and 539 once invoked, about $0.0000 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
log
Command "log" from allenc84/sapience, covering /log — judgment ledger command, routing, new assessment: /log, review: /log review [domain] and resolve: /log resolve.
md-cleanup
Unified context budget auditor — CLAUDE.md, hookify rules, memory files, skills. One command, one report. Triggers: "md cleanup", "context budget", "clean md", "audit context", "trim rules", "skill cleaning", "memory maintenance", "claudemd maintenance". NOT FOR: editing specific files (just edit), git operations…
setup-video-vision
Interactive setup wizard for claude-video-vision — configure backend, whisper, frames, and verify dependencies.
init-workspace-flow-questions
Phase 8 Questions of init-workspace-flow.
create-epo-patent
Create a complete EPO-compliant patent application from invention disclosure through filing-ready package.
memo
Search, save, inspect, and maintain memo persistent memory.