hier_config CLAUDE.md

Claude Code instructions for netdevops/hier_config, covering claude.md, self-review, benchmarks, run all benchmarks with timing output and run a specific benchmark.

Instructions file

Install

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.

agentmods
npx agentmods add instructions/netdevops/hier_config/claude-md
Clone the repo
git clone --depth 1 https://github.com/netdevops/hier_config
Per session 284 This file is loaded in full into every session.
When invoked 284 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin unknown 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 $0.00284 $0.00284
Opus 5 $0.00142 $0.00142
Sonnet 5 $0.00057 $0.00057
Haiku 4.5 $0.00028 $0.00028

Measured today against content hash 6f341a6ec33d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

hier_config CLAUDE.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.

CLAUDE.md · 26 lines

What it actually says

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

@AGENTS.md

Self-Review

Before opening or finalizing a PR, run the hier-config-review skill (/hier-config-review). It checks the diff against the repo's standards — models/typing, tests/TDD/coverage, changelog, docs, and driver patterns — and reports findings by severity.

Benchmarks

Performance benchmarks are in tests/test_benchmarks.py and are skipped by default via the benchmark pytest marker. They generate ~10,000-line configs and measure parsing, remediation, and iteration performance.

# Run all benchmarks with timing output
poetry run pytest -m benchmark -v -s

# Run a specific benchmark
poetry run pytest -m benchmark -k test_parse_large_ios_config -v -s

Use -s to see printed timing results. Each benchmark reports the best time over 3 iterations and asserts an upper bound (e.g., < 5s for parsing, < 10s for remediation). If a benchmark fails its time threshold, investigate the relevant code path for performance regressions.

After running benchmarks, always display the results to the user in a table format summarizing each benchmark's config size and elapsed time.

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. today First seen · 26 lines · 284 tokens per session scan A 6f341a6ec33d

Subscribe to this mod's changes

hier_config CLAUDE.md is an instructions file published in the GitHub repository netdevops/hier_config (150 stars, last pushed 5d ago), licensed MIT. It adds 284 tokens to every session, about $0.0014 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.