Agent skill

Invariant Check

by Ranteck in Ranteck/graph-engineer

Verify skills/graph-engineer/SKILL.md, README.md, and references/ all agree on the invariants documented in CLAUDE.md (8-node cycle, single entry point, pinned openai-codex version, DEBATE triage…

MITAuto-check passedAgent Workflows

Install Invariant Check

skills CLI
$ npx skills add Ranteck/graph-engineer --skill invariant-check -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install Ranteck/graph-engineer invariant-check --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/Ranteck/graph-engineer.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/invariant-check .claude/skills/invariant-check && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
invariant-check
GitHub stars
105
Token cost
~293 tokens
SKILL.md length
118 words
Files
1
Skills in repo
2
Repo updated
First seen
Licence
MIT

At a glance

Verify skills/graph-engineer/SKILL.md, README.md, and references/ all agree on the invariants documented in CLAUDE.md (8-node cycle, single entry point, pinned openai-codex version, DEBATE triage…

  • Tasks that involve Agent instruction files
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Invariant Check is an agent skill from Ranteck/graph-engineer. Verify skills/graph-engineer/SKILL.md, README.md, and references/ all agree on the invariants documented in CLAUDE.md (8-node cycle, single entry point, pinned openai-codex version, DEBATE triage, anti-loop cutoff, goal-template location). Use after editing any of those files, or when asked to audit/check the skill docs for consistency.

Its SKILL.md is about 290 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Agent Workflows, covering Agent instruction files. The licence is MIT.

When your agent uses it

  • Tasks that involve Agent instruction files

Example prompts

  • “/invariant-check”

What it can do on your machine

Read from SKILL.md and the folder at commit a47dbd1. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Invariant Check loads about 293 tokens when it runs. Until then it costs about 89 tokens; SKILL.md has 118 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~89
When it runs · the whole SKILL.md, loaded when a task matches
~293

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from Ranteck/graph-engineer at commit a47dbd1, republished under its MIT licence (© Ranteck). 118 words, ~293 tokens.

Download SKILL.mdSave it as .claude/skills/invariant-check/SKILL.md (or your agent's skills folder).
name
invariant-check
description
Verify skills/graph-engineer/SKILL.md, README.md, and references/ all agree on the invariants documented in CLAUDE.md (8-node cycle, single entry point, pinned openai-codex version, DEBATE triage, anti-loop cutoff, goal-template location). Use after editing any of those files, or when asked to audit/check the skill docs for consistency.
disable-model-invocation
true

Invariant Check

Dispatch the doc-consistency-reviewer subagent to audit the current state of the docs against the invariants list in /CLAUDE.md, then relay its findings verbatim (or "no issues found").

This repo has no build/test/lint step — this skill is the closest thing to a test suite it has, so run it after any non-trivial edit to SKILL.md, README.md, or a file under skills/graph-engineer/references/, and before committing doc changes.

Do not attempt to fix anything yourself as part of this skill — report only. If the reviewer finds a real mismatch, tell the user which files disagree and let them decide the fix (which version pin is current, which node name is correct, etc.) — these are content decisions, not mechanical ones.

© Ranteck, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .claude/skills/invariant-check of Ranteck/graph-engineer.

Open the folder on GitHubat commit a47dbd1

Compare with similar skills

Invariant Check next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Invariant Check compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Invariant Check this skillRanteck/graph-engineer105—~293Automated safety check: PassMIT
Neat-Freak Knowledge CloseoutKKKKhazix/khazix-skills21k—~1.9kAutomated safety check: PassMIT
Dsh Web Documentationzhu1090093659/dsh-web8.5k—~479Automated safety check: PassApache-2.0
Harness Engineering GuideOdradekAI/harness-engineering-guide1251 repos~4.3kAutomated safety check: PassApache-2.0
Agent Setup Health Audittw93/Waza7.2k—~5.2kAutomated safety check: NotesMIT
Agnixagent-sh/agnix445—~874Automated safety check: PassApache-2.0

Similar skills

  • Neat-Freak Knowledge Closeout

    KKKKhazix/khazix-skills

    Brings project docs, agent rule files, authorized memory and leftover workspace files back in line with what the code and runtime actually do at the end of a work session.

    21k GitHub stars~1.9k tokensUpdated 7 days ago
    Agent WorkflowsAuto-check passed
  • Dsh Web Documentation

    zhu1090093659/dsh-web

    A skill your agent uses when adding or editing dsh-web README files, docs, AGENTS.md instructions, user-facing configuration text, or bilingual documentation pairs.

    8.5k GitHub stars~479 tokensUpdated today
    Agent WorkflowsAuto-check passed
  • Harness Engineering Guide

    OdradekAI/harness-engineering-guide

    Audit, design, and implement AI agent harnesses for any codebase.

    125 GitHub starsUsed in 1 repo~4.3k tokens
    Agent WorkflowsAuto-check passed
  • Audits a project's agent configuration, instruction drift, hooks, MCP and AI maintainability, then reports prioritized findings with evidence and next actions.

    7.2k GitHub stars~5.2k tokensUpdated yesterday
    Agent WorkflowsAuto-check: notes
  • Agnix

    agent-sh/agnix

    A skill your agent uses when user asks to 'lint agent configs', 'validate skills', 'check CLAUDE.md', 'validate hooks', 'lint MCP'.

    445 GitHub stars~874 tokensUpdated yesterday
    Agent WorkflowsAuto-check passed
  • Setup Matt Pocock Skills

    ywwynm/EverythingDone

    Sets up an Agent skills block in AGENTS.md/CLAUDE.md and docs/agents/ so the engineering skills know this repo's issue tracker (GitHub or local markdown), triage label vocabulary, and domain doc…

    144 GitHub starsUsed in 9 repos~1.7k tokens
    Agent WorkflowsAuto-check passed

More from Ranteck/graph-engineer

  • Graph Engineer

    Ranteck/graph-engineer

    Orchestrates a Claude↔Codex cycle where Claude Code designs the contract and arbitrates, while Codex by default (via the official openai/codex-plugin-cc plugin) writes, adversarially reviews, and…

    105 GitHub stars~16k tokensUpdated 14 days ago
    Auto-check passed

Questions about Invariant Check

What does Invariant Check do?

Verify skills/graph-engineer/SKILL.md, README.md, and references/ all agree on the invariants documented in CLAUDE.md (8-node cycle, single entry point, pinned openai-codex version, DEBATE triage…. Invariant Check is an agent skill from Ranteck/graph-engineer.md (8-node cycle, single entry point, pinned openai-codex version, DEBATE triage, anti-loop cutoff, goal-template location).

When should I use Invariant Check?

Invariant Check fits situations like: tasks that involve Agent instruction files.

How do I install Invariant Check in Claude Code?

Run `npx skills add Ranteck/graph-engineer --skill invariant-check -a claude-code`. Or copy the skill folder (.claude/skills/invariant-check in Ranteck/graph-engineer) into .claude/skills/invariant-check in your project. Claude Code loads it when a task matches its description.

How do I install Invariant Check in Codex?

Run `npx skills add Ranteck/graph-engineer --skill invariant-check -a codex`. Or copy the skill folder (.claude/skills/invariant-check in Ranteck/graph-engineer) into .agents/skills/invariant-check in your project. Codex loads it when a task matches its description.

Can I use Invariant Check in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add Ranteck/graph-engineer --skill invariant-check -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/invariant-check, .gemini/skills/invariant-check, .github/skills/invariant-check and .opencode/skills/invariant-check in your project.

What does Invariant Check need to run?

SKILL.md names no scripts, command-line tools or credentials: Invariant Check is instructions for the agent only.

Does Invariant Check access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Invariant Check safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Invariant Check use?

Invariant Check is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Invariant Check use?

About 293 tokens (SKILL.md is roughly 1.2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Invariant Check?

Skills that share tags, products or a category with Invariant Check: Neat-Freak Knowledge Closeout (KKKKhazix/khazix-skills, 21k stars), Dsh Web Documentation (zhu1090093659/dsh-web, 8.5k stars), Harness Engineering Guide (OdradekAI/harness-engineering-guide, 125 stars) and Agent Setup Health Audit (tw93/Waza, 7.2k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Invariant Check?

Ranteck (a GitHub user) maintains it in Ranteck/graph-engineer, which has 105 GitHub stars. The repository holds 2 skills in this directory. The repository was last updated on September 23, 2026.

Source: Ranteck/graph-engineer on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.