Borrowing it
Nothing to install: this file belongs to gpt-cmdr/ras-commander. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/gpt-cmdr/ras-commander/main/.claude/skills/dev_human-in-loop/SKILL.mdgit clone --depth 1 https://github.com/gpt-cmdr/ras-commanderWrote 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/gpt-cmdr/ras-commander/dev_human-in-loop)<a href="https://agentmods.dev/skills/gpt-cmdr/ras-commander/dev_human-in-loop"><img src="https://agentmods.dev/badge/skills/gpt-cmdr/ras-commander/dev_human-in-loop/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/gpt-cmdr/ras-commander/dev_human-in-loop"><img src="https://agentmods.dev/badge/skills/gpt-cmdr/ras-commander/dev_human-in-loop.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00087 | $0.01216 |
| Opus 5.5 | $0.00035 | $0.00486 |
| Sonnet 5.5 | $0.00017 | $0.00243 |
| Haiku 4.5 | $0.00009 | $0.00122 |
Grade A, and why
dev_human-in-loop 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 — 165 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Human-in-the-Loop Decision Gates
Purpose
Use this skill when agent work reaches a decision point that should not be resolved by inference alone. Stop before irreversible work, professional engineering judgment, or shared workflow changes happen without a clear human decision.
Core Rule
When a hard gate is reached:
- Stop before taking the gated action.
- Summarize the decision needed and known facts.
- Provide the smallest useful option set.
- Wait for an explicit answer, or use the configured issue-control process.
- Record the decision and continue only within the approved scope.
Do not work around the gate by choosing a lower-level command, alternate tool, or indirect path that has the same effect as the gated action.
Hard Gates
Public API And Compatibility
Pause before changing interfaces or behavior that downstream users may depend on, including:
- Function signatures, return types, column names, or DataFrame schemas.
- Module paths, imports, public class names, or exported constants.
- Defaults, deprecations, removals, compatibility shims, or documented public contracts.
Ask for the intended compatibility posture: preserve, deprecate with a shim, or intentionally break with migration notes.
HEC-RAS Execution And Model Mutation
Pause before actions that run, preprocess, mutate, or overwrite HEC-RAS models when the request did not already authorize that exact operation, including:
- Computing plans or preprocessing geometry.
- Writing to original project folders instead of a destination folder.
- Reusing, deleting, or overwriting DSS, HDF, terrain, plan, geometry, or result files.
- Launching GUI automation that may trigger prompts, licensing, or long runs.
- Treating a failed or partially complete HEC-RAS run as acceptable evidence.
The decision packet must name the project, plan, executable path if relevant, destination folder, expected outputs, and how results will be verified.
Engineering Assumptions
Pause when the next step depends on a domain assumption that materially affects a hydraulic or hydrologic conclusion, including:
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 · 165 lines · 87 tokens per session scan A 343f7298261e
dev_human-in-loop is a skill published in the GitHub repository gpt-cmdr/ras-commander (88 stars, last pushed today), licensed MIT. It adds 87 tokens to every session and 1,216 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…