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/netdevops/hier_config/copilot-instructionsgit clone --depth 1 https://github.com/netdevops/hier_configWhat 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 | $0.00576 | $0.00576 |
| Opus 5 | $0.00288 | $0.00288 |
| Sonnet 5 | $0.00115 | $0.00115 |
| Haiku 4.5 | $0.00058 | $0.00058 |
Grade A, and why
hier_config 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 today.
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.
How it starts
The opening of the file, as written. The whole thing — 32 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GitHub Copilot Instructions for hier_config
hier_config is a Python library that compares network device configurations (running vs intended) and generates minimal remediation commands by parsing config text into hierarchical trees. Runtime dependencies are deliberately minimal (pydantic only).
Build & Test
All commands use poetry (not pip):
poetry run ./scripts/build.py lint-and-test # what CI runs
poetry run ./scripts/build.py pytest --coverage # 95% coverage floor
Rules to Enforce in Review
- Pydantic models must subclass the project-local
BaseModelfromhier_config/models.py(it setsfrozen=True, extra="forbid"). Direct use ofpydantic.BaseModelis a defect. - Model fields use immutable collections only:
tupleandfrozenset, neverlistorset. Rule models match config lineage withmatch_rules: tuple[MatchRule, ...]. - Strict typing: flag
Any, missing annotations (including in tests), and# type: ignore/# noqacomments without a justifying reason. mypy and pyright both run in strict mode. - Tests must accompany every code change (the project follows TDD). Tests are flat functions — no test classes (benchmarks excepted). Driver behavior changes belong in
tests/test_driver_<platform>.py; config view changes intests/config_view/. - Driver/rule changes need round-trip assertions: build running + intended configs, assert the exact remediation output (
dump_simple()), and verify the rollback restores the original (nounified_diff). - Fields on
HConfigDriverRules(hier_config/platforms/driver_base.py) use named module-level default factory functions, not lambdas. CHANGELOG.mdmust have an entry under## [Unreleased](Keep a Changelog categories: Added/Changed/Fixed/Removed, with an issue/PR reference like(#209)).- Docs must be updated when public API or driver behavior changes; new doc pages must be added to
mkdocs.ymlnav; moved pages need aredirect_mapsentry. - No loosening of quality gates: reject changes that lower coverage thresholds, disable lint rules, or relax type-checking configuration to make a change pass.
- No new runtime dependencies without prior discussion in an issue.
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.
- today First seen · 32 lines · 576 tokens per session scan A 4734726d3ee8
hier_config copilot-instructions.md is an instructions file published in the GitHub repository netdevops/hier_config (150 stars, last pushed 5d ago), licensed MIT. It adds 576 tokens to every session, about $0.0029 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 2026-09-01.
Other instructions, from other repositories
aghub CLAUDE.md
Instructions for AkaraChen/aghub, covering claude.md, project overview, common commands, build and test.
aghub AGENTS.md
Instructions for AkaraChen/aghub, covering aghub knowledge base, structure, where to look, conventions and rust.
Tutorial_AwesomeModernCPP AGENTS.md
Instructions for Awesome-Embedded-Learning-Studio/Tutorial_AwesomeModernCPP, covering agents.md, 这是什么, 通用 essentials(所有 agent 必读) and 你来做什么?(按场景路由).
grok-keysmith AGENTS.md
Instructions for Jia-Ethan/grok-keysmith, covering repository agent guide, scope, release and external state, change boundaries and documentation rules.
Tutorial_AwesomeModernCPP CLAUDE.md
Instructions for Awesome-Embedded-Learning-Studio/Tutorial_AwesomeModernCPP, covering claude.md, 写作纪律(必须遵守), 规划命令(skills,规划者模式 —— 只规划不执行), 实用命令(skills,执行型) and 记忆系统.
mcp-wireshark CLAUDE.md
Instructions for khuynh22/mcp-wireshark, covering claude.md — mcp-wireshark, purpose, architecture, code conventions and token efficiency rules.