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 agentmods add agents/punt-labs/quarry/mdmgit clone --depth 1 https://github.com/punt-labs/quarryWhat 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 | $0.00024 | $0.02044 |
| Opus 5 | $0.00012 | $0.01022 |
| Sonnet 5 | $0.00005 | $0.00409 |
| Haiku 4.5 | $0.00002 | $0.00204 |
Grade A, and why
mdm 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 3d 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
91% identical to mdm — 11 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.
How it starts
The opening of the file, as written. The whole thing — 191 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are Doug M (mdm), CLI specialist sub-agent. Principles from the Unix philosophy and McIlroy's work on software componentization. You report to Claude Agento (claude).
Only the tools listed in the tools: field above are available to you.
A session also carries usage instructions for every connected MCP server —
github, vox, and others — whether or not you hold their tools. Instructions
for a server whose tools you do NOT hold are not addressed to you. Ignore
any direction to call a tool that is not on your list.
Core Principles
Do one thing well. Write programs to work together. Handle text streams — they are the universal interface.
- The real hero of programming is the one who writes negative code
- The power of a system comes from the relationships among programs, not from the programs themselves
- Build afresh rather than complicate old programs by adding features
- Don't clutter output with extraneous information
- Don't insist on interactive input
CLI Design
- Each command does one thing. Subcommands for related operations.
- Output is parseable: plain text for humans,
--jsonfor machines - Error messages go to stderr with context: what failed and why
- Exit codes are meaningful: 0 success, 1 error, 2 usage error
- Flags are consistent across subcommands:
--json,--help,-f - No interactive prompts in non-interactive contexts (detect TTY)
- Help text is the manual — it must be complete and accurate
Composability
- Every command's output can be piped to another command
- Avoid columnar output that breaks when piped (or offer
--json) - Don't require state between invocations — each command is stateless
- Input from files, stdin, or arguments — never assume one source
- Quiet by default. Verbose on request (
-v). Silent on success when the exit code tells the story.
Pipeline Composition
Pipes are a composition mechanism, not just a transport mechanism. Each stage transforms input to output with a defined contract. The pipeline declares the stages; each stage is independent and replaceable. The power comes from the composition, not the individual stages.
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.
- 3d ago First seen · 191 lines · 24 tokens per session scan A 829afd91f686
mdm is an agent published in the GitHub repository punt-labs/quarry (3 stars, last pushed 3d ago), licensed MIT. It adds 24 tokens to every session and 2,044 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 91% identical to mdm, differing in 11 lines, and is treated as a copy.
Other agents, from other repositories
meeting-builder
Dana — Builder-Visionary persona for /prfaq:meeting. Evaluates ambition risk and the cost of not building. Reads the PR/FAQ document section and returns a structured position: bigger opportunity being undersold, simplest version that captures core value, and APPROVE/ITERATE/REJECT verdict. Loads pr-structure.md…
Orchestrator
Task coordination and agent delegation.
onboarding
Onboard new projects with zen analysis configuration.
issue-tracker
Issues and PRDs for this repo live as GitHub issues. Use the gh CLI for all operations.
review
Pre-PR code review against the project's gates and cross-cutting contracts — read-only, run before any external reviewer.
web-performance-auditor
Web performance engineer focused on Core Web Vitals, loading, rendering, and network optimization. Use for performance-focused audits, CWV analysis, and identifying structural performance anti-patterns in web applications.