narrative-drift-monitor

narrative-drift-monitor is a skill for Claude Code from aaron-he-zhu/aaron-marketing-skills. It costs 216 tokens per session (3,444 once invoked), scanned A, original, Apache-2.0.

A report that checks whether a brand's public messages have changed over time and moved away from its approved narrative. It also tracks competitor message changes and defines conditions for repositioning.

In plain words
What is it for?
It helps compare current messaging with the brand canon, review website history, monitor competitor positioning, and document when a strategic change may be justified.
Why use it?
It helps reveal gradual inconsistencies across websites and other major surfaces before they weaken the brand's identity. It also separates evidence-based repositioning from unnecessary message changes.

Skill for Claude Code

Written for Claude Code: argument-hint in frontmatter. Also seen: mentions Claude Code; built for openclaw.

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is Emit the standard shape from [skill-contract.md §Handoff Summary Format](../../../references/skill-contract.md)..

Part of the aaron-marketing plugin — 120 skills shipped together , and of aaron-marketing

Good fit It helps compare current messaging with the brand canon, review website history, monitor competitor positioning, and document when a strategic change may be justified.

Compare 6 skills from other repositories ↓
About the project

aaron-marketing-skills is a collection of 120 AI-agent skills covering marketing work such as brand narrative, search optimization, social media, email, advertising, influencer campaigns, and launches. Marketers and agent users can install it as a plugin, use its portable skills, or run its described bot team. The catalogue entries are components of this marketing workflow.

aaron-he-zhu/aaron-marketing-skills · 2,767 stars · on GitHub · aaronmarketing.ai

Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/aaron-he-zhu/aaron-marketing-skills
agentmods
npx agentmods add skills/aaron-he-zhu/aaron-marketing-skills/narrative-drift-monitor

Made for: Claude Code.

Or install aaron-marketing, the plugin that ships this one along with the rest of its 120 skills.

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 narrative-drift-monitor

README.md
[![agentmods](https://agentmods.dev/badge/skills/aaron-he-zhu/aaron-marketing-skills/narrative-drift-monitor/github.svg)](https://agentmods.dev/skills/aaron-he-zhu/aaron-marketing-skills/narrative-drift-monitor)
Your own site
<a href="https://agentmods.dev/skills/aaron-he-zhu/aaron-marketing-skills/narrative-drift-monitor"><img src="https://agentmods.dev/badge/skills/aaron-he-zhu/aaron-marketing-skills/narrative-drift-monitor/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 narrative-drift-monitor

Your own site · 80×15
<a href="https://agentmods.dev/skills/aaron-he-zhu/aaron-marketing-skills/narrative-drift-monitor"><img src="https://agentmods.dev/badge/skills/aaron-he-zhu/aaron-marketing-skills/narrative-drift-monitor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 216 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,444 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
  • Socket pass 2 Sept 2026
  • Snyk warn 2 Sept 2026
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Excessive Agency · line 68
    Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
    Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 $0.00216 $0.03444
Opus 5 $0.00108 $0.01722
Sonnet 5 $0.00043 $0.00689
Haiku 4.5 $0.00022 $0.00344

Measured 9d ago against content hash 3b5dc0db62b1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

narrative-drift-monitor 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 9d 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.

narrative/evaluate/narrative-drift-monitor/SKILL.md · 89 lines

How it starts

The opening of the file, as written. The whole thing — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Narrative Drift Monitor

Watches a live narrative for drift after it has landed — the surfaces that have quietly drifted away from the narrative-registry canon over time, the competitors that have repositioned, the explicit conditions that should (and should not) trigger a repositioning of your own message, and a D1/W1/M1 message-shift retro of intended-vs-actual pull-through. It is the last move of the TALE Evaluate phase and feeds two TALE-L items — a message-consistency pass is run before any flagship surface ships a major change and the cross-surface matches-the-canon check over time — plus it is the recorded fact base for the narrative-whiplash guardrail under A (re-cutting the narrative faster than the market can absorb it, with no triggering evidence). It measures change history with scripts/connectors/wayback.py (Measured, each snapshot carrying an as-of date) and reads competitor narrative context from category-narrative-mapper; it never scores.

Scope guard: this skill produces the drift report and repositioning-trigger set only. It does not run the first-time consistency check before a surface ships (that is narrative-cascade-planner), compute the TALE profile result or run the TALE vetoes (only the narrative-quality-auditor gate scores), measure echo rate / share-of-voice / AI-answer resonance (that is narrative-resonance-monitor), author or re-version the canon (message-system-architect proposes, narrative-registry is the sole writer of memory/narrative-registry/), or adjudicate any claim it surfaces (unverifiable claims are marked [needs source] and submitted to memory/events/claims.ndjson via an authorized operation: propose request to registry-events.py). It works one lever — drift over time — and hands off.

Read the full file on GitHub · 89 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. 9d ago First seen · 89 lines · 216 tokens per session scan A 3b5dc0db62b1

Subscribe to this mod's changes

narrative-drift-monitor is a skill published in the GitHub repository aaron-he-zhu/aaron-marketing-skills (2,767 stars, last pushed today), licensed Apache-2.0. It adds 216 tokens to every session and 3,444 once invoked, about $0.0011 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 2026-09-03.