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-dev-engineeringgit 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-dev-engineering)<a href="https://agentmods.dev/skills/elemontcapital/x-algorithm-skills/x-dev-engineering"><img src="https://agentmods.dev/badge/skills/elemontcapital/x-algorithm-skills/x-dev-engineering/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-dev-engineering"><img src="https://agentmods.dev/badge/skills/elemontcapital/x-algorithm-skills/x-dev-engineering.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 | $0.00049 | $0.00517 |
| Opus 5.5 | $0.00020 | $0.00207 |
| Sonnet 5.5 | $0.00010 | $0.00103 |
| Haiku 4.5 | $0.00005 | $0.00052 |
Grade A, and why
x-dev-engineering 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 1mo 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 — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.
X Development Engineering
Technical expertise for developing and extending the X recommendation engine, focusing on the Grok-powered Phoenix model, Rust candidate pipelines, and the removal of hand-engineered features.
Context
The modern X algorithm prioritizes a "No Hand-Engineered Features" philosophy. Relevance is learned directly from user engagement sequences using a transformer architecture.
For technical deep-dives, see:
What it does
- Implements Grok-Native Components: Guidance on integrating with the Phoenix transformer for multi-action prediction (Like, Repost, Reply, etc.).
- Architects Candidate Sources: Logic for the two primary retrieval engines: Thunder (In-Network) and Phoenix Retrieval (Out-of-Network).
- Enforces Pipeline Order: Ensures components follow the strict sequence: Query Hydration -> Sourcing -> Hydration -> Pre-Scoring Filters -> Scoring -> Selection.
- Optimizes for Parallelism: Leverages Rust's async/await to execute independent hydration and sourcing tasks concurrently.
Guidelines
- Candidate Isolation: During scoring, ensure candidates cannot "attend" to each other in the transformer. This maintains score consistency and enables batching.
- No Heuristics: Avoid adding manual "if/then" rules for relevance; the Phoenix model should handle weightings through learned engagement probabilities.
- Hydration Efficiency: Fetch only necessary metadata (text, media, author status) during the Candidate Hydration stage after initial sourcing to minimize I/O.
- Safety First: All content must pass through
VisibilityLib(Rust) for legal compliance and safety filtering before reaching the user.
Example Trigger Prompts
- "/gen-thrift new ranking signal"
- "/gen-thrift scaffold Rust Filter trait"
- "Add a new engagement signal to Phoenix prediction"
- "Show Rust implementation for Thunder candidate source"
- "Explain 'No Hand-Engineered Features' in ranking update"
- "How is candidate isolation applied in transformer attention?"
What ships with it
5 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.
- 1mo ago First seen · 43 lines · 49 tokens per session scan A a5ac8149cf22
x-dev-engineering is a skill published in the GitHub repository ElemontCapital/x-algorithm-skills (2 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 49 tokens to every session and 517 once invoked, about $0.0002 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.
Other skills, from other repositories
rn-debugging
This skill should be used when the user asks to "debug the app", "fix a crash", "diagnose a blank screen", "read error logs", "troubleshoot CDP connection", "check Metro status", "find native crashes", "inspect network failures", "the app crashed", "I see a blank screen", "the screen is white", "something broke", "app…
debug-manual
Manual debug loop with deep Belmont context and in-place spec reconciliation — user-verified fix + correct the specs that let the bug exist.
debug-auto
Auto debug loop — investigate, fix, verify using agent-dispatched pipeline.
debug
Debug router — choose between auto (agent-verified, narrow code fix) and manual (user-verified, deep spec context, in-place spec reconciliation).
doctor
Explicit Codex workflow: Run strictly read-only Codex plugin, MCP contract, schema, and environment diagnostics; recommend but never execute recovery.
debug-screen
Explicit Codex workflow: Diagnose why the current screen is broken, showing unexpected content, or crashing. Gathers parallel evidence from all layers and applies a targeted fix.