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 nexus-labs-automation/agent-observability --skill instrumentation-planninggit clone --depth 1 https://github.com/nexus-labs-automation/agent-observabilityWrote 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/nexus-labs-automation/agent-observability/instrumentation-planning)<a href="https://agentmods.dev/skills/nexus-labs-automation/agent-observability/instrumentation-planning"><img src="https://agentmods.dev/badge/skills/nexus-labs-automation/agent-observability/instrumentation-planning/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/nexus-labs-automation/agent-observability/instrumentation-planning"><img src="https://agentmods.dev/badge/skills/nexus-labs-automation/agent-observability/instrumentation-planning.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 | $0.00017 | $0.00892 |
| Opus 5 | $0.00009 | $0.00446 |
| Sonnet 5 | $0.00003 | $0.00178 |
| Haiku 4.5 | $0.00002 | $0.00089 |
Grade A, and why
instrumentation-planning 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 — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Instrumentation Planning for Agents
Plan agent observability using a tiered, outcome-focused approach.
Core Principle
Every metric and span should answer one of these questions:
- Did the agent complete its task? (success/failure)
- How long did it take? (latency)
- How much did it cost? (tokens/money)
- Why did it fail? (error context)
- What decisions did it make? (reasoning trace)
5-Tier Implementation Framework
Tier 0: Foundation (Day 1)
Essential observability to ship any agent:
- SDK initialization
- Root span for agent runs
- Unhandled error capture
- Basic success/failure status
Tier 1: Core Tracing (Week 1)
Understand agent execution:
- LLM call spans (model, latency)
- Tool execution spans (name, result)
- Agent loop iterations
- Retry attempts
Tier 2: Context & Attribution (Week 2)
Track costs and ownership:
- Token counts (input/output/total)
- Cost per call (USD)
- User/session context
- Feature/workflow attribution
Tier 3: Multi-Agent Coordination (Week 3)
For multi-agent systems:
- Parent-child span relationships
- Agent handoff tracking
- Delegation reasoning
- Supervisor decisions
Tier 4: Evaluation & Quality (Month 1)
Measure agent quality:
- Response quality scores
- Human feedback capture
- Automated eval results
- Hallucination detection signals
What NOT to Instrument
- Full prompt/response content (PII, storage cost)
- Every intermediate thought (noise)
- Timestamps as attributes (use span timing)
- User-provided secrets
Span Naming Convention
Use semantic, hierarchical names:
agent.run # Root agent execution
agent.think # Reasoning step
llm.call # LLM API call
llm.stream # Streaming LLM call
tool.execute # Tool execution
tool.validate # Tool input validation
retrieval.search # RAG retrieval
retrieval.rerank # Reranking step
memory.read # Memory fetch
memory.write # Memory store
handoff.delegate # Agent delegation
handoff.receive # Receiving delegation
human.request # Human approval request
human.response # Human response received
eval.score # Evaluation scoring
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 · 133 lines · 17 tokens per session scan A d3812c0e231c
instrumentation-planning is a skill published in the GitHub repository nexus-labs-automation/agent-observability (7 stars, last pushed 8mo ago), licensed MIT. It adds 17 tokens to every session and 892 once invoked, about $0.0001 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…