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/remember)<a href="https://agentmods.dev/commands/punt-labs/quarry/remember"><img src="https://agentmods.dev/badge/commands/punt-labs/quarry/remember/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/remember"><img src="https://agentmods.dev/badge/commands/punt-labs/quarry/remember.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 | $0.00031 | $0.00264 |
| Opus 5.5 | $0.00012 | $0.00106 |
| Sonnet 5.5 | $0.00006 | $0.00053 |
| Haiku 4.5 | $0.00003 | $0.00026 |
Grade A, and why
remember 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.
This is a copy
89% identical to remember-dev — 2 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
Input
Arguments: $ARGUMENTS
The arguments are the name for this memory, not a filename.
Task
Ask the user for the content to remember (or accept it from the conversation context if already provided).
Call mcp__quarry__remember with:
contentset to the text contentdocument_nameset to the arguments (the memory's name)agent_handleset to your own handle from the## Memoryblock in your context, when you have one — the daemon cannot infer who you are, and a subagent's working directory resolves to the repo's leader, not to youmemory_typeset to one offact,observation,procedure,opinionwhen the content fits one (lessonis reserved for/learn); leave it unset otherwise
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.
- 28d ago Changed · +2 lines 3ef62d762178
- 1mo ago Changed · +23 tokens per session 43768c1a92be
- 1mo ago First seen · 23 lines · 8 tokens per session scan A 363755d28a3b
remember is a command published in the GitHub repository punt-labs/quarry (6 stars, last pushed 2d ago), licensed MIT. It adds 31 tokens to every session and 264 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 89% identical to remember-dev, differing in 2 lines, and is treated as a copy.
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.