authority-chain

authority-chain is a skill for Claude Code, Codex from lubochka/xiigen-general-skills. It costs 23 tokens per session (175 once invoked), scanned A, original, Apache-2.0.

A method for deciding which instructions to follow when user requests, project rules, skills, and tool limits disagree. It orders those sources by authority and recency before work begins.

In plain words
What is it for?
Use it at the start of a task and whenever instructions conflict, so the agent can identify the winning rule before taking action.
Why use it?
It prevents an agent from following a lower-priority rule or habit when a higher-priority instruction applies. This reduces conflicts and unintended changes.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it at the start of a task and whenever instructions conflict, so the agent can identify the winning rule before taking action.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/lubochka/xiigen-general-skills/authority-chain
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.

Any agent
npx skills add lubochka/xiigen-general-skills --skill authority-chain
Clone the repo
git clone --depth 1 https://github.com/lubochka/xiigen-general-skills

Made for: Claude Code, Codex.

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 authority-chain

README.md
[![agentmods](https://agentmods.dev/badge/skills/lubochka/xiigen-general-skills/authority-chain/github.svg)](https://agentmods.dev/skills/lubochka/xiigen-general-skills/authority-chain)
Your own site
<a href="https://agentmods.dev/skills/lubochka/xiigen-general-skills/authority-chain"><img src="https://agentmods.dev/badge/skills/lubochka/xiigen-general-skills/authority-chain/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for authority-chain

Your own site · 80×15
<a href="https://agentmods.dev/skills/lubochka/xiigen-general-skills/authority-chain"><img src="https://agentmods.dev/badge/skills/lubochka/xiigen-general-skills/authority-chain.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 23 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 175 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.
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 $0.00023 $0.00175
Opus 5.5 $0.00009 $0.00070
Sonnet 5.5 $0.00005 $0.00035
Haiku 4.5 $0.00002 $0.00017

Measured 2mo ago against content hash a5fd7fb9e7c8, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

authority-chain 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 2mo 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.

agent-skills/authority-chain/SKILL.md · 34 lines

What it actually says

Authority Chain

Purpose

Resolve which instructions win when rules conflict.

When to Use

Use at the start of every task and whenever instructions disagree.

Inputs

User request, repository rules, project docs, local skills, and tool constraints.

Steps

  1. Identify all applicable instruction sources.
  2. Order them by authority and recency.
  3. Name conflicts before acting.
  4. Follow the highest-authority applicable rule.

Gates

No unresolved instruction conflict remains before execution.

Evidence

The final work reflects the selected rule order.

Anti-Patterns

Following agent habit over project rules; copying another project's rule file wholesale.

project-rules-first, document-hierarchy

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. 2mo ago First seen · 34 lines · 23 tokens per session scan A a5fd7fb9e7c8

Subscribe to this mod's changes

authority-chain is a skill published in the GitHub repository lubochka/xiigen-general-skills (1 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 23 tokens to every session and 175 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-08-31.

Related

authority-chain compared with skills from other repositories

authority-chain next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
authority-chainlubochka/xiigen-general-skillsSkill14mo agoApache-2.0A23Claude Code, Codex
soulaeonfun/soul.mdSkill71114d agoMITA33Claude Code, Codex
content-repurposertravisjneuman/.claudeSkill114yesterdayMITA43Claude Code
electron-desktoptravisjneuman/.claudeSkill114yesterdayMITA38Claude Code
financetravisjneuman/.claudeSkill114yesterdayMITA48Claude Code
investment-memo-generatortravisjneuman/.claudeSkill114yesterdayMITA37Claude Code
agent-seo-specialisttravisjneuman/.claudeSkill114yesterdayMITA85Claude Code