hier_config: Skill for Claude Code

.claude/skills/hier-config-review/SKILL.md

hier-config-review is a skill for Claude Code from netdevops/hier_config. It costs 46 tokens per session (884 once invoked), scanned A, original, MIT.

A review checklist for changes in the hier_config Python repository, which compares network device configurations and creates repair commands.

In plain words
What is it for?
Use it before opening or updating a pull request, or when reviewing AI-generated changes.
Why use it?
It provides a repeatable review process with repository-specific standards and required lint, test, coverage, and documentation checks.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions AGENTS.md.

This is netdevops/hier_config's own configuration. It tells Claude Code how to work on hier_config itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything hier_config configures →

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is poetry run ./scripts/build.py lint.

Reuse

Borrowing it

Nothing to install: this file belongs to netdevops/hier_config. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/netdevops/hier_config/master/.claude/skills/hier-config-review/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/netdevops/hier_config

Made for: Claude Code.

Wrote 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.

agentmods badge for hier-config-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/netdevops/hier_config/hier-config-review.svg)](https://agentmods.dev/skills/netdevops/hier_config/hier-config-review)
Your own site
<a href="https://agentmods.dev/skills/netdevops/hier_config/hier-config-review"><img src="https://agentmods.dev/badge/skills/netdevops/hier_config/hier-config-review.svg" alt="Measured on agentmods" height="20"></a>
Per session 46 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 884 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00046 $0.00884
Opus 5 $0.00023 $0.00442
Sonnet 5 $0.00009 $0.00177
Haiku 4.5 $0.00005 $0.00088

Measured 6d ago against content hash 0e9002c7889a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

hier-config-review 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 6d 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.

.claude/skills/hier-config-review/SKILL.md · 81 lines

How it starts

The opening of the file, as written. The whole thing — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.

hier_config Change Review

Review the current change set against this repository's standards and report findings. Do not fix anything unless explicitly asked — the deliverable is the review report.

Step 1: Establish the Diff

git diff master...HEAD --stat   # on a branch
git diff HEAD --stat            # fall back: uncommitted work
git diff --staged --stat        # fall back: staged only

List every changed file and classify it: library code (hier_config/), tests (tests/), docs (docs/, mkdocs.yml), CI/config, or CHANGELOG.md. Read the full diff for each classified file before judging it.

Step 2: Run the Gates

Run these and report exact failures (tool, file, line, message):

poetry run ./scripts/build.py lint
poetry run ./scripts/build.py pytest --coverage

If docs/ or mkdocs.yml changed, also run:

poetry run mkdocs build --strict

Step 3: Review by Category

Read the referenced doc before judging that category — the docs are the standard, not your intuition.

Models & Typing — read docs/dev/code-style.md

  • New Pydantic models subclass the local BaseModel (hier_config/models.py), never pydantic.BaseModel directly.
  • Model fields use tuple/frozenset, never list/set. Rule models use match_rules: tuple[MatchRule, ...].
  • No Any, no missing annotations, no unjustified # type: ignore / # noqa.
  • Lint/coverage/type-checking configuration was not loosened.

Tests & TDD — read docs/dev/testing.md

  • Every library code change has corresponding tests.
  • Tests are flat functions with full annotations; no test classes (benchmarks excepted).
  • Driver changes are tested in tests/test_driver_<platform>.py; view changes in tests/config_view/.
  • Driver/rule behavior changes include the round-trip idiom: remediation asserted via dump_simple() tuple, rollback verified via no unified_diff.
  • New fixtures live in tests/fixtures/ with module-scoped accessors in tests/conftest.py.

Read the full file on GitHub · 81 lines

Changes

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.

  1. 6d ago First seen · 81 lines · 46 tokens per session scan A 0e9002c7889a

Subscribe to this mod's changes

hier-config-review is a skill published in the GitHub repository netdevops/hier_config (149 stars, last pushed 11d ago), licensed MIT. It adds 46 tokens to every session and 884 once invoked, about $0.0002 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.

Related

Other skills, from other repositories