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 NITISH-R-G/hackerrank-orchestrate-skills --skill orchestrate-evidence-retrieval-expertgit clone --depth 1 https://github.com/NITISH-R-G/hackerrank-orchestrate-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/nitish-r-g/hackerrank-orchestrate-skills/orchestrate-evidence-retrieval-expert)<a href="https://agentmods.dev/skills/nitish-r-g/hackerrank-orchestrate-skills/orchestrate-evidence-retrieval-expert"><img src="https://agentmods.dev/badge/skills/nitish-r-g/hackerrank-orchestrate-skills/orchestrate-evidence-retrieval-expert/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/nitish-r-g/hackerrank-orchestrate-skills/orchestrate-evidence-retrieval-expert"><img src="https://agentmods.dev/badge/skills/nitish-r-g/hackerrank-orchestrate-skills/orchestrate-evidence-retrieval-expert.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 | $0.00052 | $0.00809 |
| Opus 5 | $0.00026 | $0.00404 |
| Sonnet 5 | $0.00010 | $0.00162 |
| Haiku 4.5 | $0.00005 | $0.00081 |
Grade A, and why
orchestrate-evidence-retrieval-expert 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.
How it starts
The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Orchestrate: Evidence Retrieval Expert
Evidence tier: first-hand build (August 2026). Grounded in a completed Orchestrate submission that was audited to destruction — 48 logged defects, 9 measured-and-rejected optimisations, 17 certification scripts. Every number below was measured on that system. Nothing here claims access to HackerRank's internal scoring.
The rule
Compute the ceiling before you optimise. Then benchmark the fashionable option and publish the number when it loses.
Step 1 — the pool bounds everything
No ranker can retrieve an id that is not in the pool it ranks. Measure this first:
rule-scoped pool 26/31 = 83.9% <- what ships
all-user pool 31/31 = 100% <- higher ceiling
Tempting. But measured end to end, the wider pool scored F1 0.483 vs 0.512 — the extra candidates cost more precision than the recovered recall was worth.
A higher ceiling is not a higher score.
Step 2 — benchmark the fashionable option
153 configurations (3 pools × 17 rankers × 3 values of k), scored only on labeled rows:
| ranker | F1 |
|---|---|
| BM25 | 0.512 |
| tf-idf / jaccard / hybrid | 0.496 |
| dense embeddings, RRF, cross-encoder | 0.479 |
| recency only | 0.336 |
Every neural method lost to plain lexical matching. The relation being scored was topical word overlap, not paraphrase — bi-encoders are built for the wrong thing here.
Also measured: temporal, metadata and behaviour re-ranking produced byte-identical metrics. The pools were already scoped by conversation and relationship, so applying those signals again was a no-op.
Step 3 — prefer a diagnosed mechanism over an aggregate wiggle
One ranker change was adopted, because it had a mechanism:
The correct evidence ranked 6th of 21. Cause: the similarity function divided by
min(|a|,|b|), so a short boilerplate message sharing generic terms outranked a
longer one sharing distinctive terms. Five near-duplicate 10-token messages scored
0.600; the truth, with 6 distinctive terms across 18 tokens, scored 0.389.
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 · 77 lines · 52 tokens per session scan A 155bd9101564
orchestrate-evidence-retrieval-expert is a skill published in the GitHub repository NITISH-R-G/hackerrank-orchestrate-skills (3 stars, last pushed 1mo ago), licensed MIT. It adds 52 tokens to every session and 809 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
9router-embeddings
Generate vector embeddings via 9Router /v1/embeddings using OpenAI / Gemini / Mistral / Voyage / Nvidia / GitHub embedding models for RAG, semantic search, similarity. Use when the user wants embeddings, vectors, RAG, semantic search, or to embed text.
llm-application-dev
Building applications with Large Language Models - prompt engineering, RAG patterns, and LLM integration. Use for AI-powered features, chatbots, or LLM-based automation.
karpathy-llm-wiki
Use when building or maintaining a personal LLM-powered knowledge base. Triggers: ingesting sources into a wiki, querying wiki knowledge, linting wiki quality, 'add to wiki', 'what do I know about', or any mention of 'LLM wiki' or 'Karpathy wiki'.
mongodb-search-and-ai
Guides MongoDB users through implementing and optimizing Atlas Search (full-text), Vector Search (semantic), and Hybrid Search solutions. Use this skill when users need to build search functionality for text-based queries (autocomplete, fuzzy matching, faceted search), semantic similarity (embeddings, RAG…
sqlite-vec-skilld
ALWAYS use when writing code importing "sqlite-vec". Consult for debugging, best practices, or modifying sqlite-vec, sqlite vec.
qdrant-clients-sdk
Qdrant provides client SDKs for various programming languages, allowing easy integration with Qdrant deployments.