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 agent-observabilitygit 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/agent-observability)<a href="https://agentmods.dev/skills/vodailocz/kilo-kit-mcp/agent-observability"><img src="https://agentmods.dev/badge/skills/vodailocz/kilo-kit-mcp/agent-observability/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/agent-observability"><img src="https://agentmods.dev/badge/skills/vodailocz/kilo-kit-mcp/agent-observability.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 63 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00043 | $0.01050 |
| Opus 5 | $0.00022 | $0.00525 |
| Sonnet 5 | $0.00009 | $0.00210 |
| Haiku 4.5 | $0.00004 | $0.00105 |
Grade A, and why
agent-observability 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 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.
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 — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Observability & Telemetry
Overview
This skill defines the operational standards and instrumentation requirements for monitoring agentic workflows. It ensures that complex, multi-agent systems built within KILO-KIT remain transparent, debuggable, and cost-effective. Observability in this context spans from real-time tracing of individual subagent reasoning to macro-level analysis of cost-per-task and loop-detection across distributed systems.
When To Use
Activate this skill when:
- Designing new complex agent workflows requiring distributed tracing.
- Debugging performance regressions or unexplained agent failures.
- Implementing production monitoring for cost optimization.
- Setting up feedback loops for regression testing based on real production traces.
- Configuring OpenTelemetry or integrating with observability platforms like Langfuse/Helicone.
Core Pillars
- Traceability: Capturing parent-child relationships across subagent calls and tool invocations.
- Quantification: Measuring latency, token consumption, and cache effectiveness.
- Detection: Identifying anomalies in agent behavior (e.g., infinite recursion, repetitive tool errors).
- Learning: Converting trace data into gold-standard datasets for future regression testing.
Instrumentation Workflow
To maintain high observability, follow this workflow:
- Context Propagation: Always pass
trace_idandspan_idheaders through all agent boundaries. - Structured Logging: Log all input/output payloads at the start and end of every tool call or reasoning step.
- Telemetry Standards: Use OpenTelemetry semantic conventions for LLM operations (e.g.,
llm.request.model,llm.usage.completion_tokens). - Platform Integration: Configure the agent SDKs to push spans directly to backend exporters (Langfuse/Helicone/Jaeger).
- Session Aggregation: Group all traces belonging to a single user task under a persistent
session_id.
Key Metrics
- Token Efficiency: Completion tokens vs. prompt tokens ratio.
- Cost per Task: Real-time dollar cost of the entire agentic conversation.
- Latency Breakdown: Time spent in LLM inference vs. external tool execution.
- Cache Hit Ratio: Effectiveness of persistent caching layers for repetitive queries.
- Reasoning Depth: Number of steps taken to arrive at a solution.
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 577eed21195e
- 9d ago First seen · 81 lines · 43 tokens per session scan A 0809b4885e37
agent-observability is a skill published in the GitHub repository VoDaiLocz/kilo-kit-mcp (26 stars, last pushed 4d ago), licensed Apache-2.0. It adds 43 tokens to every session and 1,050 once invoked, about $0.0002 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 2026-09-03.
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.