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 instructions/punt-labs/quarry/pythongit 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 | $0.00375 | $0.00375 |
| Opus 5 | $0.00187 | $0.00187 |
| Sonnet 5 | $0.00075 | $0.00075 |
| Haiku 4.5 | $0.00038 | $0.00038 |
Grade A, and why
quarry python.instructions.md 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 2d 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:
- vox python.instructions.md — 100% identical, 0 lines differ
What it actually says
Python Review Rules
Construction
__new__is the constructor, not__init__. Flag any__init__definition outside of@dataclassclasses.- Constructors must establish all invariants before returning. No partially-constructed objects.
@dataclassmust usefrozen=True, slots=True.
Encapsulation
- All instance attributes must start with
_(protected) or__(private). Flagself.name =without underscore. - Expose state via
@property, not public attributes.
Types
from __future__ import annotationsmust be the first import in every file.- Full type annotations on all function signatures and return types.
- Use
Protocolfor structural interfaces,ABCfor shared implementation. Neverhasattr(). - Return
NotImplementedfrom binary operators, never raiseNotImplementedError. cast()must use string form:cast("Type", val).- Import abstract types from
collections.abc, nottyping.
Error handling
- Validate at boundaries, trust internally. No defensive try/except in internal code.
- Never catch broad
Exceptionexcept at CLI entry points or MCP tool handlers. ValueErrorfor domain violations,TypeErrorfor construction bypass.
Style
ruff formatis the formatter (notblack).- Double quotes, 88-char line length.
- No backwards-compatibility shims, no
# removedtombstones.
Tools directory
tools/oo_score.pyis intentionally complex (subprocess calls to git, large check/update methods). Do not flag C901, S603, or S607 on files intools/.
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.
- 2d ago First seen · 42 lines · 375 tokens per session scan A 3c44863ec1a7
quarry python.instructions.md is an instructions file published in the GitHub repository punt-labs/quarry (3 stars, last pushed 2d ago), licensed MIT. It adds 375 tokens to every session, about $0.0019 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 instructions, from other repositories
liteparse AGENTS.md
AGENTS.md instructions for run-llama/liteparse, covering liteparse - agent documentation, project overview, key capabilities, directory structure and data flow.
ade-cli CLAUDE.md
Instructions for landing-ai/ade-cli, covering ade-cli, agent skills, issue tracker, triage labels and domain docs.
samyama-graph CLAUDE.md
Instructions for samyama-ai/samyama-graph, covering claude.md, project overview, build & development commands, build and run tests (1814 unit tests).
prfaq CLAUDE.md
Instructions for punt-labs/prfaq, covering how i write code, mandatory reading, no "pre-existing" excuse, standards and development workflow.
textbook-to-note CLAUDE.md
Instructions for drpwchen/textbook-to-note, covering claude.md — which audience are you?, working on this repo, spec before code, how much ceremony — decide before you start and the commit guard.
zer0dex AGENTS.md
Instructions for hermes-labs-ai/zer0dex, covering agents.md, use it for, do not use it for, minimal commands and output shape.