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.
npx skills add ElemontCapital/x-algorithm-skills --skill x-safety-filteringgit clone --depth 1 https://github.com/ElemontCapital/x-algorithm-skillsWrote 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.
[](https://agentmods.dev/skills/elemontcapital/x-algorithm-skills/x-safety-filtering)<a href="https://agentmods.dev/skills/elemontcapital/x-algorithm-skills/x-safety-filtering"><img src="https://agentmods.dev/badge/skills/elemontcapital/x-algorithm-skills/x-safety-filtering/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.
<a href="https://agentmods.dev/skills/elemontcapital/x-algorithm-skills/x-safety-filtering"><img src="https://agentmods.dev/badge/skills/elemontcapital/x-algorithm-skills/x-safety-filtering.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00059 | $0.00620 |
| Opus 5 | $0.00030 | $0.00310 |
| Sonnet 5 | $0.00012 | $0.00124 |
| Haiku 4.5 | $0.00006 | $0.00062 |
Grade A, and why
x-safety-filtering 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 10d 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.
How it starts
The opening of the file, as written. The whole thing — 40 lines — stays where its author put it; the contents beside it link to each section on GitHub.
X Safety & Filtering
Expert knowledge of X's VisibilityLib, covering safety labels, shadowban logic, NSFW filtering, and content health suppression mechanisms.
Context
The filtering stage is the "Gatekeeper" of the timeline. Even if a tweet has a high ML score from the Heavy Ranker, VisibilityLib can drop it entirely or apply a "Do Not Amplify" label that restricts it to the author's profile. This layer enforces legal compliance, user blocks, mutes, and platform safety rules (e.g., NSFW or Toxicity).
What it does
- Decodes "Shadowbans": Explains the specific internal labels (like
SearchBlacklist) that cause users to perceive they are shadowbanned. - Enforces User Preferences: Handles the logic for Mutes, Blocks, and "Show less often" signals.
- Manages Content Health: Identifies toxic content or misinformation using models like
pToxicityandpAbuseand applies downstream penalties. - NSFW Handling: Segments content into "Adult" or "Graphic" categories using
pNSFWMediaand ensures it respects the viewer's sensitivity settings.
Guidelines
- SafetyLevel Context: Rules are evaluated based on the
SafetyLevel(e.g., Timeline vs. Profile). A tweet might be visible on a Profile but blocked in the Home Timeline. - The "Do Not Amplify" (DNA) Label: Disqualifies tweets from the "For You" (Out-of-Network) timeline and Search results without removing them from the profile.
- Visibility vs. Ranking: 1. Pre-Scoring: Hard filters (Drop) remove blocked or legally prohibited content. 2. Post-Scoring: Soft filters (Labels) apply safety checks (e.g., author diversity) after the Heavy Ranker has assigned scores.
- Toxicity Thresholds: If a user enters a "Reply Guy" mode with consistently high
pToxicityscores, their account enters a state that limits the reach of all their future replies. - Linear Decay: Negative reputation signals follow a linear decay model; an account can "heal" its reputation over time by stopping negative behavior.
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 10d ago First seen · 40 lines · 59 tokens per session scan A 84395f82e216
x-safety-filtering is a skill published in the GitHub repository ElemontCapital/x-algorithm-skills (2 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 59 tokens to every session and 620 once invoked, about $0.0003 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.
Other skills, from other repositories
agentrq
Lead multiple agents to accomplish big tasks with specialized workspaces/agents by assigning tasks to specialized agents.
agentrq
Execute tasks assigned by humans or supervisor agents within a specific AgentRQ workspace. Use when you receive channel messages or need to report progress on tasks.
agentic
Conversational AI-first interface with minimal controls, clear outcomes, and delegated task flows for agentic workflows.
ant
Structured, enterprise-focused design system emphasizing clarity, consistency, and efficiency for data-dense web applications.
basic
Print-inspired visual language for books, magazines, and reports with editorial grids and expressive typography.
fiction
A playful, energetic, cartoonesque interface inspired by friendly children's-book illustrations — warm cream backgrounds, big bold custom display typography, saturated brand color blocks, thick black outlines, generously rounded shapes.