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.
curl -O https://raw.githubusercontent.com/netdevops/hier_config/master/.claude/skills/hier-config-review/SKILL.mdgit clone --depth 1 https://github.com/netdevops/hier_configWrote 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/skills/netdevops/hier_config/hier-config-review)<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>- NVIDIA SkillSpector pass
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 5.1 | $0.00046 | $0.00884 |
| Opus 5 | $0.00023 | $0.00442 |
| Sonnet 5 | $0.00009 | $0.00177 |
| Haiku 4.5 | $0.00005 | $0.00088 |
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.
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), neverpydantic.BaseModeldirectly. - Model fields use
tuple/frozenset, neverlist/set. Rule models usematch_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 intests/config_view/. - Driver/rule behavior changes include the round-trip idiom: remediation asserted via
dump_simple()tuple, rollback verified via nounified_diff. - New fixtures live in
tests/fixtures/with module-scoped accessors intests/conftest.py.
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.
- 6d ago First seen · 81 lines · 46 tokens per session scan A 0e9002c7889a
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.
Other skills, from other repositories
adversarial-reviewer
Adversarial code review that assumes bugs exist and hunts for them. Use when asked to review code, find bugs, audit for correctness, stress-test a PR, or when someone says "tear this apart" or "what's wrong with this". Give no benefit of the doubt — every line is guilty until proven innocent.
go-testing
Trigger: Go tests, go test coverage, Bubbletea teatest, golden files. Apply focused Go testing patterns.
semgrep-rule-variant-creator
Creates language variants of existing Semgrep rules. Use when porting a Semgrep rule to specified target languages. Takes an existing rule and target languages as input, produces independent rule+test directories for each language.
brooks-sweep
Full-sweep mode: runs a unified analysis across all quality dimensions — code decay, architecture, tech debt, and test quality — then applies fixes directly to the codebase. Safe changes are auto-applied; risky changes are confirmed before execution. Drawing on twelve classic engineering books. Triggers when: user…
include-test-files-that-assert-on-behavior-being-changed-in-decl
When delegating a task affected by this skill, include.
plugin-review
Review plugin quality with tiered checks and dependency scoping. Use for PR and pre-release audits.