A scheduled review of accepted cards in a business model to check whether their registered sources still support them. A card is a documented fact, definition, or relationship.

Use it when cards are due for review, before publishing a model, or when a fresh view of overdue and possibly outdated information is needed.

Models can become outdated when owners, sources, or process rules change, even though their links still look valid. This review makes those mismatches visible for human review.

drift-sweep — Skill for Claude Code and Codex by Vladick-Pick

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 Vladick-Pick/business-ontology --skill drift-sweep

Clone the repo

git clone --depth 1 https://github.com/Vladick-Pick/business-ontology

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/vladick-pick/business-ontology/drift-sweep/github.svg)](https://agentmods.dev/skills/vladick-pick/business-ontology/drift-sweep)

Your own site

<a href="https://agentmods.dev/skills/vladick-pick/business-ontology/drift-sweep"><img src="https://agentmods.dev/badge/skills/vladick-pick/business-ontology/drift-sweep/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/vladick-pick/business-ontology/drift-sweep"><img src="https://agentmods.dev/badge/skills/vladick-pick/business-ontology/drift-sweep.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 35 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,709 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.

Model	Per session	Once invoked
Fable 5.1	$0.00035	$0.01709
Opus 5.5	$0.00014	$0.00684
Sonnet 5.5	$0.00007	$0.00342
Haiku 4.5	$0.00003	$0.00171

Measured 2mo ago against content hash 45d5c27ac78a, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

drift-sweep 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.

skills/drift-sweep/SKILL.md · 105 lines

How it starts

The opening of the file, as written. The whole thing — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Drift sweep

Purpose

Drift is caught in two ways: on contact, when work exposes a contradiction, and on cadence, when the model deliberately checks stale cards. drift-flag handles one anchored divergence. drift-sweep is the cadence orchestrator: it finds the cards due for review, checks each against its registered source or current read-only evidence, and routes any real mismatch to drift-flag.

The sweep exists because a model of reality can go stale while still looking valid. A card can keep passing links_validate even after its owner changed, its source-of-truth moved, or a state transition grew a new exception path. The sweep does not make the agent the author of truth; it makes staleness visible before downstream agents and dashboards keep leaning on old claims.

When to use

Use this skill when:

The configured drift cadence fires.
A human asks for a review of stale or overdue cards.
Packaging or publication is about to happen and overdue next-audit cards need to be checked.
synthesize-digest needs a fresh view of what is overdue, still current, or waiting on human review.

Do not use this skill for a single contradiction encountered during normal work; call drift-flag directly. Do not use it to mine new inputs, register new sources, promote staged changes, or update accepted cards. A sweep can produce proposals and a summary; it cannot commit reality.

Inputs

Ontology root: the accepted model, 02-source-map.md, open questions, and optional registry.
Cadence date: the date used to compare next-audit.
Source access: read-only access to the registered sources needed to re-check overdue cards, bounded by each source's read policy.
Scope limit: optional list of card ids, folders, or source ids to sweep instead of the full ontology.

Procedure

Load the accepted model. Read accepted cards only. Staged proposals are visible review material, not truth.
Find due cards. Select cards whose next-audit is before the cadence date, whose last-reviewed is unknown, or whose source-map entry changed since the last review. Keep the list explicit by card id.

Read the full file on GitHub · 105 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.

2mo ago First seen · 105 lines · 35 tokens per session scan A 45d5c27ac78a

Subscribe to this mod's changes

drift-sweep is a skill published in the GitHub repository Vladick-Pick/business-ontology (3 stars, last pushed 3mo ago), licensed MIT. It adds 35 tokens to every session and 1,709 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.

Research agent-evals agent-skills ai-agents business-ontology codex ontology

drift-sweep next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
drift-sweepVladick-Pick/business-ontology	Skill	3	3mo ago	MIT	A	35	Claude Code, Codex
graph-mutation-planpotpie-ai/potpie	Skill	5.8k	8d ago	Apache-2.0	A	22	Claude Code, Codex
open-ontologiesfabio-rovai/open-ontologies	Skill	2.8k	2d ago	MIT	A	109	Claude Code
ontology-engineeringfabio-rovai/open-ontologies	Skill	2.8k	2d ago	MIT	A	47	Claude Code
basic-skilldarkrishabh/agent-skills-eval	Skill	811	2d ago	MIT	A	17	Claude Code, Codex
Rare Disease Skills Indexaristoteleo/PantheonOS	Skill	493	yesterday	BSD-2-Clause	A	43	Claude Code, Codex
objectstack-aiobjectstack-ai/objectstack	Skill	83	yesterday	Apache-2.0	A	112	Claude Code, Codex