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-input-tracinggit 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-input-tracing)<a href="https://agentmods.dev/skills/nitish-r-g/hackerrank-orchestrate-skills/orchestrate-input-tracing"><img src="https://agentmods.dev/badge/skills/nitish-r-g/hackerrank-orchestrate-skills/orchestrate-input-tracing/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-input-tracing"><img src="https://agentmods.dev/badge/skills/nitish-r-g/hackerrank-orchestrate-skills/orchestrate-input-tracing.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 | $0.00086 | $0.00676 |
| Opus 5 | $0.00043 | $0.00338 |
| Sonnet 5 | $0.00017 | $0.00135 |
| Haiku 4.5 | $0.00009 | $0.00068 |
Grade A, and why
orchestrate-input-tracing 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.
How it starts
The opening of the file, as written. The whole thing — 33 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Orchestrate: Input Tracing
Source: The Engineer's Notebook, "Getting better at HackerRank Orchestrate" (Shloka Shah) — the article's recommended self-check framework for verifying a layered agent architecture actually works as designed: pick one input and trace it through the entire system, checking where each stage occurs.
Why tracing beats reading your own architecture diagram
The article's recommended architecture separates concerns explicitly — input loading & normalization, context building, LLM invocation, response parsing & validation, schema enforcement, retry/error handling, fallback/escalation. It's easy to draw that separation and never actually confirm each stage exists as a distinct, checkable step in the running code. Tracing forces the confirmation: pick one real ticket/claim, and for each stage, answer "what did this stage receive, what did it do, what did it hand to the next stage" — concretely, not from memory of what you intended to build.
The practice
- Pick one representative input — not a trivial one, one with some real complexity (references multiple corpus documents, or has ambiguous phrasing).
- At input loading: confirm exactly what fields were extracted and normalized. Print or log the parsed representation.
- At context building: confirm exactly which corpus documents/images were retrieved for this input, and why — not just "context was built," but the actual retrieved content.
- At LLM invocation: confirm the actual prompt sent (not the template — the fully rendered prompt with this input's data substituted in).
- At response parsing: confirm what the raw model response looked like, and what your parser extracted from it.
- At validation: confirm which checks ran, and whether they passed or triggered a retry/fallback.
- At fallback/escalation (if triggered): confirm the exact condition that caused it.
If any of these steps is hard to isolate and inspect — if "context building" and "LLM invocation" are tangled into one function you can't separately observe — that's the architecture gap this trace just found, before an interviewer finds it for you.
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.
- 10d ago First seen · 33 lines · 86 tokens per session scan A 36c17114d3af
orchestrate-input-tracing is a skill published in the GitHub repository NITISH-R-G/hackerrank-orchestrate-skills (3 stars, last pushed 28d ago), licensed MIT. It adds 86 tokens to every session and 676 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.
Other skills, from other repositories
cce-routing
Use Cursor Bridge's read-only cursorcontextengine for unfamiliar project understanding when the exact code location is unknown or the task requires tracing behavior, symbols, callers and callees, data flow, registrations, interface implementations, ownership boundaries, or cross-module relationships. Trigger for…
fix-default
A default procedure for handling bug fixes, organised as a three-step scan and a CP process. The input does not explain what the three steps or CP process contain.
repair-prevention-assessment
A completion gate for fixes and self-repair work. It creates a machine-checkable assessment that separates evidence a current issue is closed from evidence that the fix will remain effective.
godot-debugging-profiling
Expert debugging workflows including print debugging (pushwarning, pusherror, assert), breakpoints (conditional breakpoints), Godot Debugger (stack trace, variables, remote debug), profiler (time profiler, memory monitor), error handling patterns, and performance optimization. Use for bug fixing, performance tuning…
godot-prompter-godot-debugging
Imported GodotPrompter guidance for godot-debugging workflows in game development projects.
godot-auditor
Godot Expert Auditor: Aurelius. Exhaustive never-list enforcement and architectural slap-down for Godot 4.7 projects.