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/vox/copilot-instructionsgit clone --depth 1 https://github.com/punt-labs/voxWrote 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/instructions/punt-labs/vox/copilot-instructions)<a href="https://agentmods.dev/instructions/punt-labs/vox/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/punt-labs/vox/copilot-instructions.svg" alt="Measured on agentmods" 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 | $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
vox copilot-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 4d 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
100% identical to quarry copilot-instructions.md — 0 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
Copilot Code Review Instructions
What to focus on
- Logic errors, off-by-one, null/None paths, unhandled edge cases
- Security: injection, credential exposure, path traversal, unsafe deserialization
- API contract violations: function returns wrong type, missing error case, changed signature without updating callers
- Concurrency issues: race conditions, shared mutable state, missing locks
- Resource leaks: unclosed files, sockets, database connections
What NOT to flag
- OO structure scores (method_ratio, encapsulation, module_size, etc.) —
tools/oo_score.pyenforces these via a ratchet mechanism. Do not duplicate its job. - New files that don't meet absolute OO thresholds — this is expected. The ratchet applies on subsequent changes.
- Formatting —
ruff formathandles this. Do not comment on whitespace, line length, quote style, or trailing commas. - Import order —
ruff check --select Ihandles this.
Do NOT suggest
- Adding
# noqa,# type: ignore,# pylint: disable, or@pytest.mark.xfailto suppress errors. The project policy is: fix the code or escalate to the operator. Suppressions require explicit operator approval. - Lowering
max-complexity, relaxing type checker strictness, or widening per-file-ignores. - Replacing
__new__with__init__— this project uses__new__as the constructor by design.
Context
This project uses an OO ratchet: make check-oo compares OO quality scores against a committed baseline (.oo-baseline.json). Every commit must improve at least one metric on touched files and regress none. The baseline is updated via make update-oo and committed alongside the code change.
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.
- 4d ago First seen · 27 lines · 375 tokens per session scan A 1a019817006f
vox copilot-instructions.md is an instructions file published in the GitHub repository punt-labs/vox (3 stars, last pushed 4d 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. It is 100% identical to quarry copilot-instructions.md, differing in 0 lines, and is treated as a copy.
Other instructions, from other repositories
prfaq CLAUDE.md
Instructions for punt-labs/prfaq, covering how i write code, mandatory reading, no "pre-existing" excuse, standards and development workflow.
z-spec CLAUDE.md
Claude Code instructions for punt-labs/z-spec, covering z-spec, mandatory reading, read this first, architecture and key architectural boundary: commands vs. surfaces.
quarry CLAUDE.md
Instructions for punt-labs/quarry, covering quarry, mandatory reading, architecture, how a query works and how ingestion works.
beadle CLAUDE.md
Instructions for punt-labs/beadle, covering beadle, what beadle is, identity, no "pre-existing" excuse and standards.
biff CLAUDE.md
Claude Code instructions for punt-labs/biff, covering how i write code, no "pre-existing" excuse, no git submodules, standards and testing pyramid.
quarry copilot-instructions.md
Instructions for punt-labs/quarry, covering copilot code review instructions, what to focus on, what not to flag, do not suggest and context.