orchestrate-self-scoring

orchestrate-self-scoring is a skill for Claude Code, Codex from NITISH-R-G/hackerrank-orchestrate-skills. It costs 88 tokens per session (1,230 once invoked), scanned A, original, MIT.

A self-review guide for estimating how a HackerRank Orchestrate submission may perform against its published scoring areas. It checks the code, agent behaviour, tools, prompts, and supporting evidence before submission.

In plain words
What is it for?
Pre-submission audits, checking for a real agent loop, reviewing tool definitions and prompts, assessing code readability, and identifying missing evidence.
Why use it?
It helps reveal the weakest part while there is still time to improve it. The review focuses on what an evaluator can verify, rather than on how much work was done.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Pre-submission audits, checking for a real agent loop, reviewing tool definitions and prompts, assessing code readability, and identifying missing evidence.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/nitish-r-g/hackerrank-orchestrate-skills/orchestrate-self-scoring
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 NITISH-R-G/hackerrank-orchestrate-skills --skill orchestrate-self-scoring
Clone the repo
git clone --depth 1 https://github.com/NITISH-R-G/hackerrank-orchestrate-skills

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.

agentmods badge for orchestrate-self-scoring

README.md
[![agentmods](https://agentmods.dev/badge/skills/nitish-r-g/hackerrank-orchestrate-skills/orchestrate-self-scoring/github.svg)](https://agentmods.dev/skills/nitish-r-g/hackerrank-orchestrate-skills/orchestrate-self-scoring)
Your own site
<a href="https://agentmods.dev/skills/nitish-r-g/hackerrank-orchestrate-skills/orchestrate-self-scoring"><img src="https://agentmods.dev/badge/skills/nitish-r-g/hackerrank-orchestrate-skills/orchestrate-self-scoring/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.

agentmods 80×15 button for orchestrate-self-scoring

Your own site · 80×15
<a href="https://agentmods.dev/skills/nitish-r-g/hackerrank-orchestrate-skills/orchestrate-self-scoring"><img src="https://agentmods.dev/badge/skills/nitish-r-g/hackerrank-orchestrate-skills/orchestrate-self-scoring.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 88 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,230 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00088 $0.01230
Opus 5 $0.00044 $0.00615
Sonnet 5 $0.00018 $0.00246
Haiku 4.5 $0.00009 $0.00123

Measured 10d ago against content hash 29eb4ea90608, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

orchestrate-self-scoring 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.

skills/orchestrate-self-scoring/SKILL.md · 71 lines

How it starts

The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Orchestrate Self-Scoring

The single highest-leverage activity in the last few hours of a timeboxed challenge is finding your own weakest dimension before a judge does — because at that point you can still act on it. This skill is a structured, honest self-audit against the four published signals, not a confidence-boosting exercise.

Ground rule: score against evidence, not effort

The instinct under deadline pressure is to score generously because you worked hard on something. Don't. Score against what a reviewer would actually see, the same evidence-anchored discipline the real scoring uses. Time spent is not evidence of quality.

The four-signal self-audit

1. Code zip (30%) — score 0–5 per row, be specific about why

Check Evidence required
Is there a genuine agent loop, or a decision tree with LLM calls in it? Point to the actual function. If you can't point to one place where the model decides what happens next, this is a decision tree.
Are tools well-named, well-described, individually testable? Open the tool definitions file. Would a stranger know when to use each tool from its description alone?
Are prompts extracted, readable, and deliberate? Are they in named files/constants, or inline f-strings?
Are failure paths (malformed output, tool error, step cap) handled explicitly? Find the code for each. If it's absent, that's a 0 on this row, not an assumption of graceful degradation.
Does the README explain design decisions, not just usage? Read it as a stranger would. Does it justify choices or only describe commands?

Run orchestrate-agent-architecture's checklist directly against your actual code, not from memory.

2. Output CSV (30%) — sample and grade, don't eyeball

Pull 5–8 rows at random (not your favorites) and grade each on the Chakra-style 4-point scale:

  • 3: specific evidence cited, KB reference is real, reasoning connects evidence to verdict
  • 2: right verdict, generic or thin justification
  • 1: wrong reasoning, or reasoning that doesn't match the verdict
  • 0: no real justification present

Read the full file on GitHub · 71 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.

  1. 10d ago First seen · 71 lines · 88 tokens per session scan A 29eb4ea90608

Subscribe to this mod's changes

orchestrate-self-scoring is a skill published in the GitHub repository NITISH-R-G/hackerrank-orchestrate-skills (3 stars, last pushed 29d ago), licensed MIT. It adds 88 tokens to every session and 1,230 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.

Related

Other skills, from other repositories

general

Handle everyday conversation, answer questions, manage files, take notes, run scripts, and maintain persistent memory across sessions. Use when the user asks a general question, requests file operations, wants to brainstorm ideas, needs to-do tracking, asks you to remember something, or requests skill search and…

0xranx/golembot · 61 tokens

multi-bot

Coordinates responses between multiple GolemBot instances in a shared fleet. Use when the bot operates in a group chat with other bots, needs to decide whether to respond or pass, or must call a peer bot's API to fetch cross-domain data.

0xranx/golembot · 53 tokens

kb-guide

Search, read, create, and update knowledge base entries via MCP-connected KB tools. Use when the user asks to look up documentation, find existing articles, check if docs exist on a topic, create a new KB entry, update an existing document, or when domain questions should be answered from the knowledge base first.

0xranx/golembot · 66 tokens

ops

Content operations assistant — drafts blog posts, social media copy, and marketing materials, compiles data briefings, and tracks competitor activity. Use when the user asks to write a blog post, draft social media content, create marketing copy, generate a weekly report, compile operational metrics, update the…

0xranx/golembot · 67 tokens

escalation

Escalate unresolvable or sensitive requests to a human agent by recording an escalation entry. Use when the user asks to speak to a human, the bot cannot answer confidently, the request involves financial, legal, or security concerns, a safety issue is detected, or the user is frustrated after repeated failures.

0xranx/golembot · 66 tokens

code-review

Reviews code changes, pull requests, and diffs for correctness, security, performance, and style. Use when the user submits a PR for review, asks to review a diff or code snippet, or requests a quality check on recent changes.

0xranx/golembot · 51 tokens