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-multimodal-evidence-groundinggit 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-multimodal-evidence-grounding)<a href="https://agentmods.dev/skills/nitish-r-g/hackerrank-orchestrate-skills/orchestrate-multimodal-evidence-grounding"><img src="https://agentmods.dev/badge/skills/nitish-r-g/hackerrank-orchestrate-skills/orchestrate-multimodal-evidence-grounding/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-multimodal-evidence-grounding"><img src="https://agentmods.dev/badge/skills/nitish-r-g/hackerrank-orchestrate-skills/orchestrate-multimodal-evidence-grounding.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 | $0.00103 | $0.00870 |
| Opus 5 | $0.00051 | $0.00435 |
| Sonnet 5 | $0.00021 | $0.00174 |
| Haiku 4.5 | $0.00010 | $0.00087 |
Grade A, and why
orchestrate-multimodal-evidence-grounding 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 — 38 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Orchestrate: Multi-Modal Evidence Grounding
Direct evidence: the multi-modal-review challenge's required output schema includes supporting_image_ids (which specific images support the verdict), claim_status_justification (evidence-grounded explanation), and a three-way claim_status split between supported, contradicted, and not_enough_information — a structurally different decision space from a binary yes/no.
Why the three-way split is the core design challenge
Collapsing contradicted and not_enough_information into one "reject" bucket is the most likely single design mistake in this challenge, because they mean genuinely different things and likely warrant different downstream handling:
contradicted: the image evidence actively conflicts with the claim (e.g., claim describes water damage, image shows no visible water damage on the claimed component) — a confident, evidence-backed negative.not_enough_information: the image doesn't clearly show enough to judge either way (wrong angle, too dark, wrong object entirely, image doesn't cover the claimed damage area) — an honest "we can't tell," structurally the same category as the "mark uncertainty" discipline inorchestrate-failure-handling, just domain-specific to this challenge.
A system that only ever outputs supported or contradicted, never not_enough_information, is almost certainly over-confident — real claim photos are frequently ambiguous, off-angle, or incomplete, and a system that forces every case into a confident verdict is exhibiting exactly the "guessing instead of marking uncertainty" failure mode the organizers warn against generally.
Evidence citation, per-verdict
supporting_image_ids and claim_status_justification together are the schema's evidence-anchoring mechanism — directly analogous to Chakra's own scoring philosophy (traceable to a specific, verbatim moment). A justification like "the image shows clear denting consistent with the claimed impact" citing image_003 is checkable; "the evidence supports the claim" with no image ID is not, and reads the same way a vague interview answer reads to an evidence-anchored scorer.
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 · 38 lines · 103 tokens per session scan A 18e801ae8557
orchestrate-multimodal-evidence-grounding is a skill published in the GitHub repository NITISH-R-G/hackerrank-orchestrate-skills (3 stars, last pushed 1mo ago), licensed MIT. It adds 103 tokens to every session and 870 once invoked, about $0.0005 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
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…
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.
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.
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…
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.
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.