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 agentmods add instructions/elemontcapital/x-algorithm-skills/agents-mdgit 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/instructions/elemontcapital/x-algorithm-skills/agents-md)<a href="https://agentmods.dev/instructions/elemontcapital/x-algorithm-skills/agents-md"><img src="https://agentmods.dev/badge/instructions/elemontcapital/x-algorithm-skills/agents-md.svg" alt="Measured on agentmods" 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 | $0.01220 | $0.01220 |
| Opus 5 | $0.00610 | $0.00610 |
| Sonnet 5 | $0.00244 | $0.00244 |
| Haiku 4.5 | $0.00122 | $0.00122 |
Grade A, and why
x-algorithm-skills AGENTS.md 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 4d 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 — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
🤖 Agent Integration Guide
This repository follows the Agent Skills Standard, a specification for providing AI agents with domain-specific "expertise" through structured documentation and reference material.
While optimized for Claude Code via its native plugin system, this repository is designed to be "Agent Agnostic"—working seamlessly with Cursor, GitHub Copilot, Windsurf, Roo Code, and custom LLM implementations.
🧠 Core Agent Personas
Following the Vercel Agent Skills model, we categorize our skills into specialized personas.
You can "summon" these personas by providing the corresponding SKILL.md files to your agent.
📈 The Growth Architect (x-post-optimizer)
- Best for: Viral content strategy and reach optimization.
- Key Files:
.../x-post-optimizer/SKILL.md,references/engagement-multipliers.md
🏗️ The System Designer (x-architecture & x-retrieval-systems)
- Best for: Understanding the macro-flow from retrieval to timeline delivery.
- Key Files:
.../x-architecture/SKILL.md,.../x-retrieval-systems/SKILL.md
🧠 The ML Specialist (x-ranking-engine & x-experimental-ops)
- Best for: Deep-dives into MaskNet scoring and A/B test analysis.
- Key Files:
.../x-ranking-engine/SKILL.md,.../x-experimental-ops/SKILL.md
🛠️ The Algorithm Engineer (x-dev-engineering)
- Best for: Writing Rust/Scala code and modifying Thrift schemas.
- Key Files:
.../x-dev-engineering/SKILL.md,references/rust-pipeline.md
⚖️ The Trust & Safety Auditor (x-data-signals & x-safety-filtering)
- Best for: Investigating shadowbans, reputation, and toxicity filtering.
- Key Files:
.../x-data-signals/SKILL.md,.../x-safety-filtering/SKILL.md
📋 Skill Discovery Dashboard
| Skill | Role | Core Capability |
|---|---|---|
| x-post-optimizer | Content Strategist | Optimizes reach via HeavyRanker weight alignment. |
| x-architecture | System Architect | Maps HomeMixer and candidate generation flows. |
| x-ranking-engine | ML Engineer | Audits MaskNet scoring and MTL probability heads. |
| x-dev-engineering | Software Engineer | Assists with Rust/Scala interop and Thrift definitions. |
| x-data-signals | Data Scientist | Explains SimClusters, TweepCred, and RealGraph. |
| x-safety-filtering | Safety Analyst | Decodes VisibilityLib labels and shadowban logic. |
| x-retrieval-systems | Search Engineer | Manages Earlybird indices and ANN vector search. |
| x-experimental-ops | Product Manager | Tracks DuckDuckGoose tests and "North Star" metrics. |
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.
- 4d ago First seen · 84 lines · 1,220 tokens per session scan A d83dde3bad04
x-algorithm-skills AGENTS.md is an instructions file published in the GitHub repository ElemontCapital/x-algorithm-skills (2 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 1,220 tokens to every session, about $0.0061 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 instructions, from other repositories
cctop AGENTS.md
AGENTS.md instructions for st0012/cctop, covering agents.md - development guide for cctop, scope and sources, required development rules, driver workflow and github and pr rules.
toh-framework CLAUDE.md
Claude Code instructions for wasintoh/toh-framework, covering claude.md — toh framework (repo development guide), what this is, everyday commands, verification protocol and single source, transformed per ide.
examples CLAUDE.md
Claude Code instructions for rossoctl/examples, covering claude.md - agent examples, repository structure, key commands, code style and dco sign-off (mandatory).
agent-rules child-process.instructions.md
Instructions for lirantal/agent-rules, covering system processes secure coding guidelines, your mission and spawning system processes.
claude-code-templates CLAUDE.md
Claude Code instructions for Justdvp/claude-code-templates, covering claude.md, project overview, development commands, package management and application commands.
deckforge AGENTS.md
Instructions for tph-kds/deckforge, covering deckforge agent entry point, code intelligence, read order, default routing and non-negotiable implementation rules.