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 VoDaiLocz/kilo-kit-mcp --skill human-in-the-loopgit clone --depth 1 https://github.com/VoDaiLocz/kilo-kit-mcpWrote 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/vodailocz/kilo-kit-mcp/human-in-the-loop)<a href="https://agentmods.dev/skills/vodailocz/kilo-kit-mcp/human-in-the-loop"><img src="https://agentmods.dev/badge/skills/vodailocz/kilo-kit-mcp/human-in-the-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/vodailocz/kilo-kit-mcp/human-in-the-loop"><img src="https://agentmods.dev/badge/skills/vodailocz/kilo-kit-mcp/human-in-the-loop.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 | $0.00042 | $0.00843 |
| Opus 5 | $0.00021 | $0.00421 |
| Sonnet 5 | $0.00008 | $0.00169 |
| Haiku 4.5 | $0.00004 | $0.00084 |
Grade C, and why
human-in-the-loop scanned grade C with 1 finding 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 5d 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
- Before performing destructive file operations (e.g., `rm -rf`, bulk overwrites). How it starts
The opening of the file, as written. The whole thing — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Human-in-the-Loop (HITL) Patterns
Overview
The "Human-in-the-Loop" (HITL) skill provides a standardized framework for integrating human oversight into agentic workflows. By tiering actions based on risk, we ensure autonomy is utilized safely for low-impact tasks while maintaining rigorous human control over high-impact operations. This skill aligns with the C4 Runtime Protocol to prevent "black box" agent behavior.
When To Use
- Before performing destructive file operations (e.g.,
rm -rf, bulk overwrites). - Before triggering deployment pipelines or infrastructure changes.
- Before making financial or security-impacting decisions.
- When an agent's confidence in a plan or outcome is below a critical threshold.
- When the user requires explicit auditability of agent intent.
Risk-Tiered Action Matrix
To manage friction, apply the appropriate gate based on the action category:
| Tier | Category | Mechanism | User UX |
|---|---|---|---|
| 0 | Informational | Auto-Approve | Logged in background/console. |
| 1 | Standard Edit | Warn/Confirm | Inline diff preview + "Proceed". |
| 2 | Destructive/Critical | Hard Gate | Explicit approval required; blocked until sign-off. |
| 3 | Financial/Deployment | Multi-Factor/Formal Audit | Requires explicit sign-off via UI/Artifact link. |
Checkpoint Design Patterns
- The Plan Preview: Agents must expose the plan artifact before execution.
- Structured Clarification: Use tool-based, multi-choice queries to reduce ambiguity, avoiding open-ended questions that fatigue users.
- Delta Validation: Always present a
diffor specific "what is changing" summary before writing. - Resumption Points: Save state tokens to ensure that if a session drops, the human can review the exact state, modify if needed, and resume.
Implementation Workflow
- Identify Risk: Evaluate the proposed task against the Risk-Tiered Action Matrix.
- Surface Intent: Generate an "Action Summary" using the
ask_questiontool or an artifact. - Await Authorization: Use non-blocking pauses (or asynchronous messaging) to wait for approval.
- Execute with Trace: Perform the action under a logging wrapper that records the authorized state ID.
- Verify: Immediately follow with a verification check to confirm the expected outcome.
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.
- 5d ago Changed scan D → C 5bbf6288b2ae
- 9d ago First seen · 61 lines · 42 tokens per session scan D 32e4dad84127
human-in-the-loop is a skill published in the GitHub repository VoDaiLocz/kilo-kit-mcp (26 stars, last pushed 4d ago), licensed Apache-2.0. It adds 42 tokens to every session and 843 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
llm-structured-output
Get reliable JSON, enums, and typed objects from LLMs using responseformat, tooluse, and schema-constrained decoding across OpenAI, Anthropic, and Google APIs.
drizzle-orm-expert
Expert in Drizzle ORM for TypeScript — schema design, relational queries, migrations, and serverless database integration. Use when building type-safe database layers with Drizzle.
landing-page-generator
Generates high-converting Next.js/React landing pages with Tailwind CSS. Uses PAS, AIDA, and BAB frameworks for optimized copy/components (Heroes, Features, Pricing). Focuses on Core Web Vitals/SEO.
tdmcp-pipeline
Orchestrates the tdmcp feature team end-to-end: design/wireframe → build → integrate → QA → release. Use whenever the user wants to build, implement, develop, ship, or add one or more tdmcp features/tools/effects/controls/AI-prompts for TouchDesigner, or to run them through a coordinated design→develop→QA→deploy…
startcycle-graph-user
Use when a task needs a small, throwaway multi-agent fan-out (a couple of parallel workers plus a review pass) in ANY project, without the full /startcycle-graph contract — no .agents/graph.md bootstrap, no state.json schema, no persistent files. Model-tiered by role (opus plan, sonnet review, haiku or an external CLI…
memb-skill
BDB local-first long-term memory engine (memB). Use when querying, remembering, or adapting preferences, code architectures, and developer patterns across tasks.