A guided toolkit for reporting fake accounts, impersonation, deepfakes, stolen media, or scam advertisements on major online platforms. It gathers evidence and prepares a report draft, while the affected person submits it.

Use it to capture evidence, obtain the platform-specific reporting steps, and draft a takedown notice for human review before submission.

It helps preserve proof before content changes and reduces the need to search for each platform's reporting process from scratch.

takedown — Skill for Claude Code and Codex by Deirfgeiz

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 Deirfgeiz/officialai-takedown-skill --skill officialai-takedown-skill

Clone the repo

git clone --depth 1 https://github.com/Deirfgeiz/officialai-takedown-skill

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/deirfgeiz/officialai-takedown-skill/officialai-takedown-skill/github.svg)](https://agentmods.dev/skills/deirfgeiz/officialai-takedown-skill/officialai-takedown-skill)

Your own site

<a href="https://agentmods.dev/skills/deirfgeiz/officialai-takedown-skill/officialai-takedown-skill"><img src="https://agentmods.dev/badge/skills/deirfgeiz/officialai-takedown-skill/officialai-takedown-skill/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/deirfgeiz/officialai-takedown-skill/officialai-takedown-skill"><img src="https://agentmods.dev/badge/skills/deirfgeiz/officialai-takedown-skill/officialai-takedown-skill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 86 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 742 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	$0.00086	$0.00742
Opus 5	$0.00043	$0.00371
Sonnet 5	$0.00017	$0.00148
Haiku 4.5	$0.00009	$0.00074

Measured 11d ago against content hash 423730d6454e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

takedown 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 11d 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.

SKILL.md · 61 lines

How it starts

The opening of the file, as written. The whole thing — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Takedown Skill

You are helping someone get impersonating or stolen content removed from a platform (Meta/Facebook/Instagram, YouTube, TikTok, X, or Google). The Official AI free tier does the deterministic work; your job is to guide the human through it accurately and without overpromising.

Ground rules

Evidence first, always. Content gets deleted or edited once the poster is reported. Capture evidence BEFORE discussing anything else.
You draft; the human files. Every notice is a DRAFT until the affected person (or their authorized representative) reviews it and submits it. Platform notices carry legal liability for misrepresentation, so never present a draft as ready-to-send without their review.
Never guess platform process facts. The playbook data carries citations and marks unverifiable facts UNVERIFIED; relay them that way.
You are not a lawyer and this is not legal advice; say so if the situation is contested (fair use claims, disputes between known parties, anything beyond routine impersonation/stolen-content reports).

Workflow

Capture: call capture_evidence with the URL of the fake post or profile (plus direct media URLs when the user has them). Save the returned manifest.id.
Pick the path: call get_playbook for the platform. Choose the report path whose legal basis fits:
- Fake account pretending to be the person: *.impersonation
- Their own photo/video reposted without permission: *.copyright (if they took or own the media) or the likeness/privacy path
- AI-generated likeness (deepfake): the platform's likeness or privacy path (YouTube: youtube.privacy_likeness)
- Scam ad using their face: google.ads.deceptive_ads or meta.both.scam_ads
Collect the claimant's details: full name, email, mailing address (needed for copyright notices), country, and whether they are the affected person or an authorized representative.
Draft: call draft_notice with the report path, manifest id, claimant, a description of the original work or persona, and the factual infringement description. Supply platform-specific values (like the reported username) via extraFields.
Hand over: show the draft, the filing instructions (form URL or documented email intake), and any missing fields. The human completes ID uploads and submits.
Optional: check_authorization tells you whether content matches a registered authentic work in the Official AI registry. An "unknown" result is not a judgment about the content.

Read the full file on GitHub · 61 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.

11d ago First seen · 61 lines · 86 tokens per session scan A 423730d6454e

Subscribe to this mod's changes

takedown is a skill published in the GitHub repository Deirfgeiz/officialai-takedown-skill (0 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 86 tokens to every session and 742 once invoked, about $0.0004 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 2026-08-31.

Legal and compliance

specification-writing

A workflow for writing complete patent specifications from patent claims and an invention disclosure. It adapts the document to a chosen jurisdiction, such as the US, Europe, or China.

wanshuiyin/Auto-claude-code-research-in-sleep · 49 tokens

regulatory-research-fallback

Fallback workflow for regulatory research when web extraction tools fail on government PDFs.

HKUDS/OpenSpace · 20 tokens

x-scorecard

OpenSSF Scorecard for assessing open source project security. Check security best practices and compliance. Dependency: This is an x-cmd module. Install x-cmd first (see x-cmd skill for installation options). see x-cmd skill for installation.

x-cmd/x-cmd · 57 tokens

gesellschaftsrechtliche-satzungen-agb

Für Gesellschaftsrechtliche Satzungen AGB Abgrenzung: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt. Fachgebiet: AGB-Recht-Prüfer. Route: gesellschaftsrechtliche-satzungen-agb.

Klotzkette/claude-fuer-deutsches-recht · 69 tokens

memstack-business-gdpr

Use this skill when the user says 'GDPR', 'data protection', 'privacy compliance', 'DPA', 'DSAR', 'data subject request', 'cookie consent', 'privacy audit', 'CCPA', or asks 'do I need GDPR for this repo'. Scans the repository to detect what personal data is collected, classifies sensitivity, determines whether GDPR…

cwinvestments/memstack · 121 tokens

nda-review

Use when the user uploads or pastes a non-disclosure agreement and asks for review, redline, risk assessment, or a recommendation on whether to sign. Identifies missing standard protections, one-sided or unusual provisions, and operational issues; produces a structured report with severity ratings and citations to…

LegalQuants/lq-ai · 79 tokens